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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and programming-related function names

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

    programming method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteBarrier
    -0.90
    MemoryWarning
    -0.81
    onedDateTime
    -0.81
    DockStyle
    -0.79
     disambiguazione
    -0.78
    tagHelperRunner
    -0.78
    iſen
    -0.77
    ロウィン
    -0.74
    ſelves
    -0.74
     RouterModule
    -0.74
    POSITIVE LOGITS
    .
    0.40
     lan
    0.35
     j
    0.35
     ne
    0.35
     "
    0.35
     in
    0.35
     Ne
    0.34
     Moy
    0.33
     en
    0.33
     M
    0.33
    Act Density 0.000%

    No Known Activations