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

    Neuronpedia

    INDEX
    Explanations

    Sentiment polarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шиб
    -0.06
     RAID
    -0.06
    _elt
    -0.06
     Fee
    -0.06
    乂
    -0.06
    ت
    -0.06
    Nombre
    -0.06
    ��
    -0.06
     FLT
    -0.06
    olulu
    -0.06
    POSITIVE LOGITS
     Authorization
    0.07
     guit
    0.07
     sat
    0.07
     آزاد
    0.07
    -generator
    0.06
     hindi
    0.06
    .Entity
    0.06
    laden
    0.06
    mpl
    0.06
     regimen
    0.06
    Act Density 0.007%

    No Known Activations