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

    Neuronpedia

    INDEX
    Explanations

    sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.53
    arXiv
    -0.51
     Cond
    -0.50
     "
    -0.49
    RTLD
    -0.49
     rev
    -0.49
    scriptcase
    -0.48
    &__
    -0.48
     fal
    -0.47
     “
    -0.46
    POSITIVE LOGITS
     itſelf
    0.75
    łaś
    0.66
     myſelf
    0.66
     viață
    0.64
     barbarians
    0.63
     ainfi
    0.61
     Moslem
    0.61
    capace
    0.60
    łby
    0.60
     Saltar
    0.60
    Act Density 0.033%

    No Known Activations