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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ceans
    -0.07
    (Be
    -0.07
    iště
    -0.07
    descending
    -0.07
    orama
    -0.07
    roids
    -0.07
    ิตย
    -0.07
    ensor
    -0.06
     sanitary
    -0.06
    Proposal
    -0.06
    POSITIVE LOGITS
    _delay
    0.07
    iku
    0.06
    }=
    0.06
     VER
    0.06
     trail
    0.06
     вода
    0.06
     few
    0.06
     カ
    0.05
    -package
    0.05
     tanı
    0.05
    Act Density 0.004%

    No Known Activations