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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Garc
    -0.07
    azard
    -0.07
    .findall
    -0.07
    OUSE
    -0.07
     amort
    -0.07
    уж
    -0.06
    warz
    -0.06
     lust
    -0.06
     松
    -0.06
    Then
    -0.06
    POSITIVE LOGITS
    _false
    0.07
     Essen
    0.06
    	UI
    0.06
    (prom
    0.06
    ("----------------
    0.06
    always
    0.06
     universal
    0.06
    _relationship
    0.06
     navigationOptions
    0.06
     making
    0.06
    Act Density 0.033%

    No Known Activations