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

    Neuronpedia

    INDEX
    Explanations

    requires

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jorge
    -0.08
    .Integer
    -0.07
    ประ
    -0.07
    _GO
    -0.07
    يخ
    -0.07
    .IsSuccess
    -0.07
     minded
    -0.07
     Гор
    -0.07
     sass
    -0.07
    €“
    -0.06
    POSITIVE LOGITS
    기술
    0.07
     Reject
    0.07
    Ｌ
    0.07
     reductions
    0.06
     wearer
    0.06
     고객
    0.06
    远离
    0.06
     upbringing
    0.06
     indicators
    0.06
     teammate
    0.06
    Act Density 0.006%

    No Known Activations