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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .inf
    -0.07
     conf
    -0.07
     uranus
    -0.07
     Celtic
    -0.06
    oyal
    -0.06
    AF
    -0.06
    Business
    -0.06
    Reporting
    -0.06
    izabeth
    -0.06
    SEX
    -0.06
    POSITIVE LOGITS
    ait
    0.07
     UserDao
    0.07
     живот
    0.06
    ded
    0.06
    ザー
    0.06
    -after
    0.06
    .method
    0.05
    -delay
    0.05
    orrar
    0.05
     scales
    0.05
    Act Density 0.000%

    No Known Activations