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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Width
    -0.08
    opies
    -0.07
    orderBy
    -0.06
     attribute
    -0.06
     hazard
    -0.06
    Como
    -0.06
     Asp
    -0.06
    uitka
    -0.06
    Secure
    -0.06
     concerts
    -0.06
    POSITIVE LOGITS
    elerinde
    0.07
     konz
    0.07
     :|
    0.07
     ['#
    0.06
    劇
    0.06
    _PAYMENT
    0.06
    .__
    0.06
    /vendors
    0.06
    body
    0.06
     TV
    0.06
    Act Density 0.023%

    No Known Activations