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

    Neuronpedia

    INDEX
    Explanations

    code and programming snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Action
    -0.07
    onclick
    -0.06
    ิญญ
    -0.06
     muster
    -0.06
    .Background
    -0.06
     suicide
    -0.06
     inspectors
    -0.06
     silently
    -0.06
    ';↵↵↵
    -0.06
    disabled
    -0.06
    POSITIVE LOGITS
    odzi
    0.07
    аними
    0.07
    .eof
    0.06
     roadmap
    0.06
    _closure
    0.06
    “For
    0.06
     overlapping
    0.06
    _ATTACHMENT
    0.06
    šek
    0.06
    TRAIN
    0.06
    Act Density 0.014%

    No Known Activations