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

    Neuronpedia

    INDEX
    Explanations

    thefts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compositions
    -0.07
    .directory
    -0.06
    isposable
    -0.06
    .iv
    -0.06
     çeşit
    -0.06
     "");
    -0.06
    getContext
    -0.06
    23
    -0.06
     quotation
    -0.06
    +$
    -0.06
    POSITIVE LOGITS
    isman
    0.07
    ナル
    0.06
     burgeoning
    0.06
     shooters
    0.06
     Phong
    0.06
     QFont
    0.06
    ANNOT
    0.06
    begin
    0.06
     جن
    0.06
    攝
    0.06
    Act Density 0.016%

    No Known Activations