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

    Neuronpedia

    INDEX
    Explanations

    sentencing guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Code
    -0.07
     captions
    -0.07
     diversas
    -0.06
     formas
    -0.06
    utos
    -0.06
     Did
    -0.06
    _frequency
    -0.06
     characters
    -0.06
    Privacy
    -0.06
     Marino
    -0.06
    POSITIVE LOGITS
     nějaký
    0.06
     bulundu
    0.06
     nabízí
    0.06
     Berg
    0.06
    ierge
    0.06
    Thank
    0.06
    ΑΜ
    0.06
    인데
    0.06
     strom
    0.06
     HDC
    0.06
    Act Density 0.009%

    No Known Activations