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

    Neuronpedia

    INDEX
    Explanations

    Metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <!
    -0.08
    .integer
    -0.08
    🍉
    -0.08
    peng
    -0.07
     Mot
    -0.07
    _pri
    -0.07
     Enrique
    -0.07
    .FileInputStream
    -0.07
    ❕
    -0.07
    	freopen
    -0.07
    POSITIVE LOGITS
     metadata
    0.09
    Normalized
    0.08
     أو
    0.08
    metadata
    0.07
     parasite
    0.07
     locating
    0.07
    最初的
    0.07
    ure
    0.07
    low
    0.07
    UARIO
    0.07
    Act Density 0.005%

    No Known Activations