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

    Neuronpedia

    INDEX
    Explanations

    questions or directives related to data retrieval and manipulation

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

    questions and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.72
    GraphicsUnit
    -0.72
    ValueStyle
    -0.71
    CloseOperation
    -0.70
    yntaxException
    -0.69
    :✨
    -0.68
     Infórmanos
    -0.67
    ymce
    -0.63
    EDEFAULT
    -0.63
    iibo
    -0.63
    POSITIVE LOGITS
     should
    0.37
     Scholz
    0.36
     trotzdem
    0.33
    om
    0.32
    ld
    0.31
    cu
    0.31
     permettre
    0.30
     said
    0.30
    mb
    0.30
     safe
    0.29
    Act Density 0.234%

    No Known Activations