Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conditional phrases related to legal responsibilities or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a conditional conjunction

    np_acts-logits-general · gemini-2.0-flash

    conditional clauses and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вот
    -0.57
     sûr
    -0.53
    woordig
    -0.52
     navidad
    -0.49
     siquiera
    -0.49
     teď
    -0.48
    akterysty
    -0.48
    TileEntity
    -0.48
     Suddenly
    -0.48
    のが
    -0.47
    POSITIVE LOGITS
     sufficient
    0.85
    tagHelperRunner
    0.75
     such
    0.73
    OGND
    0.73
     adequate
    0.72
     protoimpl
    0.72
     proposed
    0.70
    RenderAtEndOf
    0.70
     fufficient
    0.67
     CreateTagHelper
    0.67
    Act Density 0.891%

    No Known Activations