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

    Neuronpedia

    INDEX
    Explanations

    es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     то
    -0.07
    priority
    -0.07
    raq
    -0.07
    不安
    -0.07
    ьми
    -0.07
    smart
    -0.07
    atty
    -0.07
     больш
    -0.07
    antaged
    -0.07
    Many
    -0.07
    POSITIVE LOGITS
     Ges
    0.07
     ấn
    0.07
     expression
    0.07
    วง
    0.06
     undes
    0.06
     Lam
    0.06
    .XtraEditors
    0.06
     expressions
    0.06
    Ven
    0.06
     exercise
    0.06
    Act Density 0.009%

    No Known Activations