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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Era
    -0.07
     ber
    -0.06
     sailors
    -0.06
    ався
    -0.06
    ูนย
    -0.06
    _letters
    -0.06
    .CLASS
    -0.06
     Guil
    -0.06
     Tarif
    -0.06
    (obs
    -0.06
    POSITIVE LOGITS
    (audio
    0.07
    str
    0.07
     ultimo
    0.07
    aged
    0.06
    Sign
    0.06
     Alpha
    0.06
    elly
    0.06
    stead
    0.06
    ‪
    0.06
    velopment
    0.06
    Act Density 0.009%

    No Known Activations