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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疁
    -0.09
     Cuomo
    -0.09
    .React
    -0.08
    ivirus
    -0.08
    .appendTo
    -0.08
     Clemson
    -0.08
    -player
    -0.08
     males
    -0.08
    🐧
    -0.08
    пре
    -0.08
    POSITIVE LOGITS
     meant
    0.08
    ˸
    0.07
    �
    0.07
     frequent
    0.07
     ::↵
    0.07
     relation
    0.07
    Both
    0.07
     Lok
    0.06
     bek
    0.06
    _ll
    0.06
    Act Density 0.003%

    No Known Activations