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

    Neuronpedia

    INDEX
    Explanations

    regular/periodic occurrence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assumed
    -0.07
    chrift
    -0.07
    광
    -0.07
     DVDs
    -0.06
    STYPE
    -0.06
    ceiving
    -0.06
     상황
    -0.06
     deposited
    -0.06
    بد
    -0.06
    fade
    -0.06
    POSITIVE LOGITS
     ارتف
    0.07
     amusing
    0.06
     strengthens
    0.06
     Strict
    0.06
    mpr
    0.06
    _HOT
    0.06
    idla
    0.06
     boğ
    0.06
     τρο
    0.06
    _READONLY
    0.06
    Act Density 0.640%

    No Known Activations