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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _object
    -0.07
     verifies
    -0.07
     nutrit
    -0.07
     simplex
    -0.06
    acock
    -0.06
    _service
    -0.06
     Paladin
    -0.06
    _definition
    -0.06
     interv
    -0.06
    ,row
    -0.06
    POSITIVE LOGITS
    ああ
    0.07
    纪
    0.07
    록
    0.06
    浩
    0.06
    /story
    0.06
    塔
    0.06
    厅
    0.06
    忙
    0.06
    рач
    0.06
     ((_
    0.06
    Act Density 0.020%

    No Known Activations