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

    Neuronpedia

    INDEX
    Explanations

    copyright notices in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fm
    -0.07
     επα
    -0.07
    ีบ
    -0.06
    ？」
    -0.06
    chema
    -0.06
    lä
    -0.06
     sucks
    -0.06
     ομά
    -0.06
     Mùa
    -0.06
    chemas
    -0.06
    POSITIVE LOGITS
     cones
    0.07
     Structural
    0.06
     Toe
    0.06
     Cut
    0.06
    CAR
    0.06
    knife
    0.06
    _erase
    0.06
    -gradient
    0.06
     Electronics
    0.06
    _READ
    0.06
    Act Density 0.004%

    No Known Activations