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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    sequence-level special control/header tokens (like the <|begin_of_text|>, <|end_header_id|>, and other metadata boundary markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ỏ
    -0.06
    ecut
    -0.06
    حت
    -0.06
    الي
    -0.06
    cook
    -0.06
     poss
    -0.06
    776
    -0.06
    Mini
    -0.06
     �
    -0.06
    отор
    -0.06
    POSITIVE LOGITS
     cartesian
    0.07
     bieten
    0.07
     Notices
    0.07
     breeds
    0.07
     subtype
    0.06
     Serialized
    0.06
     callbacks
    0.06
    VERTISE
    0.06
    .Transform
    0.06
     slices
    0.06
    Act Density 5.753%

    No Known Activations