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
     FileWriter
    -0.07
     threat
    -0.07
     upp
    -0.06
    DLL
    -0.06
     splits
    -0.06
    repos
    -0.06
     mutated
    -0.06
    Min
    -0.06
     Famil
    -0.06
     naked
    -0.06
    POSITIVE LOGITS
     dolay
    0.07
    (cols
    0.07
    @end
    0.07
     Provided
    0.06
    .delegate
    0.06
    =get
    0.06
     francaise
    0.06
    wp
    0.06
    isObject
    0.06
     anyway
    0.06
    Act Density 0.013%

    No Known Activations