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

    Neuronpedia

    INDEX
    Explanations

    Math and programming contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     —
    -0.08
    anding
    -0.08
    izations
    -0.08
    ization
    -0.07
     также
    -0.07
    ieving
    -0.07
    lications
    -0.07
    ‍,
    -0.07
    ——
    -0.07
     ასევე
    -0.07
    POSITIVE LOGITS
    _fee
    0.08
     täysin
    0.08
    /new
    0.08
     unieke
    0.08
    )↵
    0.08
     única
    0.08
     unik
    0.08
    Không
    0.08
    ):
    0.08
     sèl
    0.08
    Act Density 0.085%

    No Known Activations