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

    Neuronpedia

    INDEX
    Explanations

    number or count

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enjo
    -0.07
    (bl
    -0.07
     redundant
    -0.07
     zwarte
    -0.07
     informatie
    -0.07
    _Time
    -0.06
    _intersection
    -0.06
    _thumb
    -0.06
     tvar
    -0.06
     liners
    -0.06
    POSITIVE LOGITS
    ức
    0.06
     Players
    0.06
    ۱۴
    0.06
    出し
    0.06
    .Error
    0.06
     returning
    0.06
    خل
    0.06
    Aff
    0.06
     :↵
    0.06
    charging
    0.06
    Act Density 0.122%

    No Known Activations