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

    Neuronpedia

    INDEX
    Explanations

    contact

    np_max-act · gemini-2.0-flash

    The neuron activates on placeholder name‐tokens (e.g. “NAME_1,” “NAME_2,” etc.) in the drafts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     beautiful
    -0.06
     Sho
    -0.06
    .hasMore
    -0.06
    ByUrl
    -0.06
    篇
    -0.06
    .SetParent
    -0.06
    因
    -0.06
     Voll
    -0.06
     Veterinary
    -0.06
     sensual
    -0.06
    POSITIVE LOGITS
    PET
    0.07
    CGFloat
    0.06
     cloning
    0.06
    .ย
    0.06
    95
    0.06
    47
    0.06
    год
    0.06
    89
    0.06
    gio
    0.06
     داخلی
    0.06
    Act Density 0.027%

    No Known Activations