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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ymbol
    -0.07
    azed
    -0.07
    ubbo
    -0.07
    ErrorResponse
    -0.06
    _DGRAM
    -0.06
    SSI
    -0.06
    rooms
    -0.06
    azure
    -0.06
    ایان
    -0.06
    etc
    -0.06
    POSITIVE LOGITS
     immortal
    0.08
     Inserts
    0.08
    из
    0.07
    場合は
    0.06
     picturesque
    0.06
     살
    0.06
     Prevent
    0.06
    _should
    0.06
    луб
    0.06
     プ
    0.06
    Act Density 0.020%

    No Known Activations