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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive and does not detect any specific patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (home
    -0.06
    ativos
    -0.06
    :::|
    -0.06
    ﾍ
    -0.06
    -scenes
    -0.06
    (bg
    -0.06
     rush
    -0.06
     Schwar
    -0.06
    Contours
    -0.06
     ﾍ
    -0.06
    POSITIVE LOGITS
    asses
    0.07
    ава
    0.07
     deform
    0.06
    ічна
    0.06
     область
    0.06
    MLE
    0.06
    Eq
    0.06
    angelog
    0.06
    _TEST
    0.06
    equiv
    0.06
    Act Density 0.002%

    No Known Activations