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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    очка
    -0.07
    ipar
    -0.07
    Misc
    -0.06
    uC
    -0.06
     ún
    -0.06
    dest
    -0.06
    -builder
    -0.06
     Yoshi
    -0.06
    enez
    -0.06
    atég
    -0.06
    POSITIVE LOGITS
     그림
    0.07
     Lat
    0.07
    (states
    0.07
    执
    0.06
    /release
    0.06
     Subscription
    0.06
     preprocessing
    0.06
    OLF
    0.06
    _normalized
    0.06
    _behavior
    0.06
    Act Density 0.006%

    No Known Activations