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

    Neuronpedia

    INDEX
    Explanations

    Legal context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _builtin
    -0.07
    ไร
    -0.07
    Mexico
    -0.07
     unfolds
    -0.07
    -running
    -0.06
    엔
    -0.06
     rouge
    -0.06
    われる
    -0.06
    -direct
    -0.06
     contingency
    -0.06
    POSITIVE LOGITS
    aliyet
    0.06
     civilian
    0.06
     Cem
    0.06
     dean
    0.06
     kararı
    0.06
     ASAP
    0.06
    _PART
    0.06
    *N
    0.06
    лим
    0.06
     Heads
    0.05
    Act Density 0.013%

    No Known Activations