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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.87
    IntoConstraints
    -0.85
     resourceCulture
    -0.84
     createState
    -0.83
    InjectAttribute
    -0.82
    AndEndTag
    -0.76
    writeFieldEnd
    -0.76
    Архівовано
    -0.73
     <=",
    -0.73
    Datuak
    -0.71
    POSITIVE LOGITS
    teri
    0.50
     relâche
    0.41
    sizeof
    0.39
     Ráp
    0.39
    af
    0.39
     sizeof
    0.38
     effetto
    0.38
     efeitos
    0.38
     Unidas
    0.38
     Rij
    0.37
    Act Density 0.001%

    No Known Activations