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

    Neuronpedia

    INDEX
    Explanations

    Windows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commerciales
    -0.08
     flyer
    -0.07
     Christi
    -0.07
    vät
    -0.07
     Biz
    -0.07
    割合
    -0.07
    แตก
    -0.07
     interf
    -0.07
     diab
    -0.07
     validity
    -0.07
    POSITIVE LOGITS
    .cfg
    0.08
    ского
    0.08
    ারা
    0.08
    Ã
    0.08
     motto
    0.08
     কর্ত
    0.08
    Logging
    0.07
    -built
    0.07
    Authenticator
    0.07
     encompassing
    0.07
    Act Density 0.007%

    No Known Activations