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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yan
    -0.07
     Hold
    -0.07
    topia
    -0.07
     enum
    -0.07
     listar
    -0.07
    ytä
    -0.07
    deposit
    -0.07
    listing
    -0.07
    axx
    -0.07
     proteins
    -0.07
    POSITIVE LOGITS
    Difference
    0.10
    _difference
    0.10
     quotient
    0.09
     diferenças
    0.09
     difference
    0.09
     numerator
    0.09
     différence
    0.09
     différences
    0.09
     imme
    0.08
    цом
    0.08
    Act Density 0.023%

    No Known Activations