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

    Neuronpedia

    INDEX
    Explanations

    Real-world examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lings
    -2.48
     himself
    -1.86
     Himself
    -1.34
    himself
    -1.28
     himſelf
    -0.95
     herself
    -0.74
     thyself
    -0.72
     oneself
    -0.71
    他自己
    -0.71
     istrinya
    -0.70
    POSITIVE LOGITS
     الحره
    0.64
    ruptedException
    0.59
    ArgsConstructor
    0.55
    smallskip
    0.52
    cire
    0.51
     atas
    0.51
    cij
    0.50
    cheon
    0.49
     eius
    0.49
    dillera
    0.48
    Act Density 0.088%

    No Known Activations