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

    Neuronpedia

    INDEX
    Explanations

    Confront

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ощи
    -0.07
    .TabStop
    -0.07
    魔法
    -0.06
    KEEP
    -0.06
    us
    -0.06
    ух
    -0.06
    яг
    -0.06
     appare
    -0.06
    ungi
    -0.06
    uses
    -0.06
    POSITIVE LOGITS
     impressed
    0.06
    (Fl
    0.06
    .asp
    0.06
    eled
    0.06
    /****************************************************************
    0.06
    (F
    0.06
    _allocate
    0.06
     vulnerability
    0.06
     incident
    0.06
     مى
    0.06
    Act Density 0.001%

    No Known Activations