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

    Neuronpedia

    INDEX
    Explanations

    shrinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     찬
    -0.07
     alan
    -0.06
     stride
    -0.06
     Individuals
    -0.06
    namen
    -0.06
     детей
    -0.06
     lesb
    -0.06
     Sele
    -0.06
    준
    -0.05
    .lazy
    -0.05
    POSITIVE LOGITS
    science
    0.07
    VisualStyle
    0.07
     quart
    0.07
    .double
    0.07
     excluded
    0.07
     anthrop
    0.07
     shootout
    0.07
    .tile
    0.07
    ifying
    0.06
    ients
    0.06
    Act Density 0.000%

    No Known Activations