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

    Neuronpedia

    INDEX
    Explanations

    severed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    centaje
    -0.07
    >You
    -0.07
    cyan
    -0.06
    ้จ
    -0.06
    iteral
    -0.06
    (row
    -0.06
     Courtesy
    -0.06
     eş
    -0.06
    icers
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     FIRE
    0.07
    .atom
    0.07
    -res
    0.07
     žád
    0.06
    that
    0.06
     інозем
    0.06
    ishment
    0.06
    _proto
    0.06
    .In
    0.06
     letto
    0.06
    Act Density 0.000%

    No Known Activations