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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ज
    -0.06
    ация
    -0.06
    PHP
    -0.06
    OS
    -0.06
    Ze
    -0.06
    DDD
    -0.06
    ifact
    -0.06
    _BASE
    -0.06
    DEM
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Launching
    0.07
     localObject
    0.06
     weight
    0.06
    regunta
    0.06
    -outline
    0.06
    /Object
    0.06
     rue
    0.06
     realization
    0.06
     масло
    0.06
     goofy
    0.06
    Act Density 0.043%

    No Known Activations