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

    Neuronpedia

    INDEX
    Explanations

    code expressions and lambdas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अभिने
    0.42
    燜
    0.41
    BOL
    0.40
    .$.
    0.40
    Voices
    0.39
     ന്
    0.39
    Gas
    0.38
     Technical
    0.38
    collectibles
    0.38
     निर्
    0.38
    POSITIVE LOGITS
     lichaam
    0.44
     translate
    0.41
     lemons
    0.41
     lambda
    0.41
     translates
    0.41
     expression
    0.40
    Expression
    0.40
     expresión
    0.39
     Lambda
    0.38
     body
    0.38
    Act Density 0.007%

    No Known Activations