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

    Neuronpedia

    INDEX
    Explanations

    quantities and identification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    os
    -0.08
    мов
    -0.07
    едагог
    -0.07
    ska
    -0.07
    ordion
    -0.06
    _modify
    -0.06
    회
    -0.06
    徳
    -0.06
    .vn
    -0.06
    c
    -0.06
    POSITIVE LOGITS
    taboola
    0.07
     Οικο
    0.07
     Rebellion
    0.06
    .performance
    0.06
     potrav
    0.06
     temples
    0.06
     Fairy
    0.06
     со
    0.06
    !important
    0.06
     onay
    0.06
    Act Density 0.044%

    No Known Activations