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

    Neuronpedia

    INDEX
    Explanations

    Exercise routines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lottery
    -0.08
     kindergarten
    -0.08
     ballot
    -0.08
    生日
    -0.08
     Vacc
    -0.08
     cumpleaños
    -0.08
    _runs
    -0.08
     countdown
    -0.08
     bapt
    -0.07
     Lottery
    -0.07
    POSITIVE LOGITS
     rowing
    0.08
     magnetic
    0.08
     rumm
    0.08
     peito
    0.08
     पुल
    0.08
    иё
    0.08
    SYM
    0.08
    vpn
    0.08
     decoding
    0.07
    神器
    0.07
    Act Density 0.002%

    No Known Activations