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

    Neuronpedia

    INDEX
    Explanations

    derivatives and exponentials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    έρα
    -0.08
     cowboy
    -0.08
    frist
    -0.08
    ర్స
    -0.08
     imprisonment
    -0.08
     foydalan
    -0.08
    _trip
    -0.08
    упить
    -0.08
    零钱
    -0.08
     }↵↵↵//
    -0.08
    POSITIVE LOGITS
     Szen
    0.08
     inter
    0.08
     lines
    0.07
     YES
    0.07
     hanno
    0.07
     permitem
    0.07
     cron
    0.07
    ुभ
    0.07
    hd
    0.07
     Aure
    0.07
    Act Density 0.011%

    No Known Activations