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

    Neuronpedia

    INDEX
    Explanations

    appellant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reshold
    -0.07
    oriously
    -0.07
    举
    -0.07
     Они
    -0.06
     Preston
    -0.06
     если
    -0.06
     ему
    -0.06
    听到
    -0.06
    -phone
    -0.06
     の
    -0.06
    POSITIVE LOGITS
    isation
    0.07
    _Task
    0.06
     impeccable
    0.06
    าช
    0.06
    Advertis
    0.06
    contres
    0.06
    nad
    0.06
    اعد
    0.06
    duğ
    0.06
    िलन
    0.06
    Act Density 0.008%

    No Known Activations