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

    Neuronpedia

    INDEX
    Explanations

    instances of function declarations and method calls in programming contexts

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

    "for (int i =" or "for (int j =" loops

    np_acts-logits-general · gemini-2.0-flash

    `++` and loop variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.73
    "
    -0.66
    ellyn
    -0.63
    -[
    -0.60
    -“
    -0.58
    ].(
    -0.54
     down
    -0.54
    -0.52
    richTextPanel
    -0.52
    [.
    -0.51
    POSITIVE LOGITS
     ++
    1.31
    ++
    0.87
    ++$
    0.75
    InjectAttribute
    0.75
    ArgsConstructor
    0.73
     +++
    0.73
    batore
    0.67
     Normdatei
    0.63
    enumi
    0.63
    plusplus
    0.61
    Act Density 0.011%
    No Known Activations