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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مباش
    -0.07
    atio
    -0.07
     kell
    -0.06
    _LOADED
    -0.06
     كور
    -0.06
     uydu
    -0.06
     Kadın
    -0.06
    .php
    -0.06
     But
    -0.06
    rowad
    -0.06
    POSITIVE LOGITS
    304
    0.06
    .uml
    0.06
    原
    0.06
     Races
    0.06
    nation
    0.06
    .Description
    0.06
    Imm
    0.06
    ป
    0.06
     konumu
    0.06
    mentioned
    0.06
    Act Density 0.011%

    No Known Activations