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

    Neuronpedia

    INDEX
    Explanations

    common words and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loneliness
    -0.07
     rude
    -0.06
     Arn
    -0.06
    алізації
    -0.06
     scape
    -0.06
    .band
    -0.06
    ite
    -0.06
    ility
    -0.06
    opc
    -0.05
    бра
    -0.05
    POSITIVE LOGITS
    /testing
    0.07
    .getRuntime
    0.07
    _POSITION
    0.07
     CircularProgressIndicator
    0.07
     FontWeight
    0.07
     staggering
    0.06
    .Display
    0.06
    uego
    0.06
    java
    0.06
     actualizar
    0.06
    Act Density 0.000%

    No Known Activations