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

    Neuronpedia

    INDEX
    Explanations

    contracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mine
    -0.08
     cake
    -0.08
    REAT
    -0.07
     tiener
    -0.07
    Practice
    -0.06
     Neutral
    -0.06
    -gen
    -0.06
    iscard
    -0.06
     Cake
    -0.06
     başlay
    -0.06
    POSITIVE LOGITS
     directional
    0.07
    (",",
    0.07
    限制
    0.06
    Unauthorized
    0.06
    行
    0.06
    เง
    0.06
     saturated
    0.06
     диаг
    0.06
     fontFamily
    0.06
    cpt
    0.06
    Act Density 0.025%

    No Known Activations