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

    Neuronpedia

    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash

    markers that denote the beginning of a speaker/header section in the conversation formatting (conversation boundary/header delimiters).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    323
    -0.08
    &amp
    -0.07
     فراهم
    -0.07
    -IS
    -0.07
     aun
    -0.07
     Zust
    -0.07
    便
    -0.06
    _arrow
    -0.06
    424
    -0.06
     真
    -0.06
    POSITIVE LOGITS
    ../../../
    0.07
    čka
    0.07
     �
    0.07
    _configs
    0.07
    化学
    0.06
    лоб
    0.06
     #'
    0.06
    interfaces
    0.06
    گو
    0.06
    (Role
    0.06
    Act Density 0.242%

    No Known Activations