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

    Neuronpedia

    INDEX
    Explanations

    method chaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @Injectable
    -0.06
     출장
    -0.06
     Pioneer
    -0.06
    _payload
    -0.06
     "?"
    -0.05
     Specific
    -0.05
     gift
    -0.05
     관
    -0.05
     maj
    -0.05
    (er
    -0.05
    POSITIVE LOGITS
    ONA
    0.08
     extracting
    0.07
    onation
    0.07
     WC
    0.07
    continent
    0.07
     ignoring
    0.07
    lanan
    0.07
    iske
    0.07
    pone
    0.07
    unan
    0.07
    Act Density 0.000%

    No Known Activations