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

    Neuronpedia

    INDEX
    Explanations

    missing information

    np_max-act · gemini-2.0-flash

    This neuron detects messages indicating zero or no user‐generated content (e.g. “no reviews,” “no questions,” “currently no…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    '}).
    -0.07
     smoothly
    -0.06
     вся
    -0.06
    .metro
    -0.06
    　i
    -0.06
     nig
    -0.06
     tutto
    -0.06
    .SelectedIndex
    -0.06
    ,index
    -0.06
     elementos
    -0.06
    POSITIVE LOGITS
    魂
    0.07
    088
    0.07
    opsis
    0.07
    uitive
    0.07
     wishing
    0.06
    Expr
    0.06
    pee
    0.06
     elseif
    0.06
    abyte
    0.06
    ическая
    0.06
    Act Density 0.009%

    No Known Activations