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

    Neuronpedia

    INDEX
    Explanations

    impossibility/negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -address
    -0.07
    _redis
    -0.06
     respectfully
    -0.06
    .ld
    -0.06
    Coupon
    -0.06
     Ala
    -0.06
    准
    -0.06
    oubles
    -0.06
    OTOS
    -0.06
     през
    -0.06
    POSITIVE LOGITS
     reg
    0.07
     Everton
    0.07
     variation
    0.07
    ？」
    0.07
     prosecutor
    0.06
     ►
    0.06
     ch
    0.06
    。",↵
    0.06
     suicides
    0.06
    .False
    0.06
    Act Density 0.100%

    No Known Activations