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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash

    This neuron activates on phrases that introduce or point to a subsequent list or set of items (e.g. “the following,” “use the following”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    reeze
    -0.07
    .std
    -0.07
     broken
    -0.07
    ющей
    -0.06
     want
    -0.06
     ли
    -0.06
     WAN
    -0.06
    all
    -0.06
     ratt
    -0.06
     stamps
    -0.06
    POSITIVE LOGITS
    osi
    0.07
     Increment
    0.07
    .SimpleDateFormat
    0.07
    _combo
    0.06
     dü
    0.06
    �
    0.06
    .Intent
    0.06
     Daten
    0.06
    能力
    0.06
    _skill
    0.06
    Act Density 0.016%

    No Known Activations