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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash

    The neuron responds to floating-point number tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Hit
    -0.07
     основном
    -0.07
    Tot
    -0.07
    52
    -0.07
    véd
    -0.07
     El
    -0.07
    ğinden
    -0.07
     chú
    -0.07
     postponed
    -0.07
     популяр
    -0.07
    POSITIVE LOGITS
     under
    0.10
     Under
    0.09
    Under
    0.07
     UNDER
    0.07
    egree
    0.06
    assign
    0.06
    ictionary
    0.06
     artworks
    0.06
    \Action
    0.05
    iae
    0.05
    Act Density 0.015%

    No Known Activations