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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    assertTrue
    -0.07
     Appro
    -0.07
     intervention
    -0.07
     Otto
    -0.06
     thoroughly
    -0.06
    (targets
    -0.06
    -0.06
     Airbus
    -0.06
     عبار
    -0.06
     taking
    -0.06
    POSITIVE LOGITS
     catastrophe
    0.07
    .sul
    0.06
     надання
    0.06
    舍
    0.06
     saç
    0.06
     lane
    0.06
    )'),
    0.06
    алізації
    0.06
     chatter
    0.06
    데이트
    0.05
    Act Density 0.009%

    No Known Activations