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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lambda
    -0.07
     постоя
    -0.07
     snapped
    -0.07
    iever
    -0.07
    �
    -0.07
    蛞
    -0.07
     desperate
    -0.07
    רמת
    -0.06
    �
    -0.06
     shoulder
    -0.06
    POSITIVE LOGITS
     [\
    0.08
     mismo
    0.07
    所能
    0.07
    \">"
    0.07
    vais
    0.07
     Gard
    0.06
    Conference
    0.06
     Pháp
    0.06
    משק
    0.06
    pas
    0.06
    Act Density 0.108%

    No Known Activations