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

    Neuronpedia

    INDEX
    Explanations

    chart performance

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (especially decimal‐formatted chart positions and similar numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.06
     Cached
    -0.06
     není
    -0.06
    ated
    -0.06
    izations
    -0.06
    الش
    -0.06
    či
    -0.06
     yapmış
    -0.06
    Ô
    -0.06
    ług
    -0.06
    POSITIVE LOGITS
    _rank
    0.06
    Andre
    0.06
    Personal
    0.06
     Webb
    0.06
    .Kind
    0.06
    .transfer
    0.06
     junior
    0.06
    Heart
    0.06
     deg
    0.06
     SNAP
    0.06
    Act Density 0.006%

    No Known Activations