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

    Neuronpedia

    INDEX
    Explanations

    corporate releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nuevo
    -0.07
    ，你
    -0.07
     drunk
    -0.06
     Dry
    -0.06
     Renewable
    -0.06
    _IDENTIFIER
    -0.06
     Specific
    -0.06
    Hip
    -0.06
    quire
    -0.06
    bbing
    -0.06
    POSITIVE LOGITS
     addAction
    0.07
    :Is
    0.07
    @
    0.07
     obyvatel
    0.07
     tato
    0.07
    _mC
    0.07
    lpVtbl
    0.07
    xlim
    0.06
     TensorFlow
    0.06
    armac
    0.06
    Act Density 0.018%

    No Known Activations