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

    Neuronpedia

    INDEX
    Explanations

    specially formatted characters or tokens indicative of specific programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    user reporters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.46
    ari
    -0.38
    ;
    -0.38
    mobileqq
    -0.37
    ),
    -0.35
    Hauptartikel
    -0.35
    …
    -0.34
     into
    -0.34
     onto
    -0.34
    AB
    -0.33
    POSITIVE LOGITS
    mybatisplus
    0.68
     Infórmanos
    0.68
    󠁢
    0.65
     kasarigan
    0.65
    IntoConstraints
    0.63
     femininas
    0.61
    يميديا
    0.60
    󠁴
    0.59
     zijne
    0.58
    Tikang
    0.57
    Act Density 0.003%

    No Known Activations