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

    Neuronpedia

    INDEX
    Explanations

    programming syntax related to conditional statements and functions

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

    Code snippets or programming-related keywords

    np_acts-logits-general · gemini-2.0-flash

    code comments and programming keywords multi-language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.86
    )))));
    -0.64
    )))
    -0.63
    )
    -0.62
    ')],
    -0.59
     parseFrom
    -0.56
    <eos>
    -0.56
    Демографія
    -0.54
    endregion
    -0.54
    ]])
    -0.53
    POSITIVE LOGITS
    ArgsConstructor
    0.58
    mặt
    0.57
     كومونز
    0.56
     Infórmanos
    0.56
     cherchés
    0.55
    tagHelperRunner
    0.51
    IUrlHelper
    0.51
    THON
    0.51
    منابع
    0.50
     obverse
    0.50
    Act Density 0.087%

    No Known Activations