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

    Neuronpedia

    INDEX
    Explanations

    Probability calculations with letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gard
    -0.07
     Moody
    -0.06
     because
    -0.06
     Abe
    -0.06
     Celsius
    -0.06
     Ahmad
    -0.06
    potential
    -0.06
     pacientes
    -0.06
    波
    -0.06
     çocuk
    -0.06
    POSITIVE LOGITS
    UNC
    0.07
    าหล
    0.07
    습
    0.07
     Brah
    0.07
     numberOf
    0.07
    _EXTENDED
    0.07
    especially
    0.06
     centerY
    0.06
    |string
    0.06
     techno
    0.06
    Act Density 0.009%

    No Known Activations