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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (labels
    -0.06
    	op
    -0.06
     Cao
    -0.06
    -symbol
    -0.06
    	tab
    -0.06
    Po
    -0.06
     Mitar
    -0.06
    'O
    -0.06
     conqu
    -0.05
    Fee
    -0.05
    POSITIVE LOGITS
    dart
    0.07
    rowad
    0.07
     miles
    0.07
    .sql
    0.07
    =add
    0.07
    有的
    0.07
    .about
    0.06
    _lua
    0.06
    .maxLength
    0.06
    .／
    0.06
    Act Density 0.002%

    No Known Activations