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

    Neuronpedia

    INDEX
    Explanations

    code block termination symbols

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

    Code or configuration file syntax

    np_acts-logits-general · gemini-2.0-flash

    code block start/end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.72
     للمعارف
    -0.71
     CreateTagHelper
    -0.71
     ejus
    -0.70
     GenerationType
    -0.70
    Revenir
    -0.64
    GraphicsUnit
    -0.64
    elemField
    -0.63
    AddTagHelper
    -0.63
    حياتها
    -0.62
    POSITIVE LOGITS
    ↵↵↵↵
    0.62
    ">)</
    0.60
    +");
    0.56
     متعلقه
    0.56
    ("}");
    0.55
    ↵↵↵
    0.55
    ↵↵↵↵↵
    0.53
    uzi
    0.52
    "]();
    0.51
    ])))
    0.51
    Act Density 0.062%

    No Known Activations