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

    Neuronpedia

    INDEX
    Explanations

    to or will

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases expressing uncertainty about future events (e.g. don’t know, going to, will, what kind).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _malloc
    -0.07
     k
    -0.07
    ูไ
    -0.07
    _variant
    -0.07
    \Facades
    -0.07
    MMdd
    -0.07
     سود
    -0.06
    べて
    -0.06
    flatMap
    -0.06
     MEDIATEK
    -0.06
    POSITIVE LOGITS
    billing
    0.07
     manifestations
    0.06
    ทำงาน
    0.06
     Config
    0.06
     Shapes
    0.06
    effect
    0.06
     assay
    0.06
     Exhibit
    0.06
    structions
    0.06
    onor
    0.06
    Act Density 0.022%

    No Known Activations