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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IIIK
    -0.06
     "@"
    -0.06
    澳
    -0.06
     incor
    -0.06
     erklä
    -0.06
    .phase
    -0.05
     челов
    -0.05
     unf
    -0.05
    �
    -0.05
     �
    -0.05
    POSITIVE LOGITS
    _sign
    0.08
    Res
    0.07
     Al
    0.07
     injected
    0.07
    _Al
    0.07
     гар
    0.07
    ALLOW
    0.07
    override
    0.07
     obtaining
    0.07
     Implements
    0.07
    Act Density 0.003%

    No Known Activations