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

    Neuronpedia

    INDEX
    Explanations

    code assignments and variable initialization in programming scripts

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

    code, punctuation, and control characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.59
    ########.
    -0.49
    ształ
    -0.44
    ContentAsync
    -0.43
    AnimationsModule
    -0.42
     ujednoznacz
    -0.41
    RegressionTest
    -0.40
    AsUp
    -0.40
    riez
    -0.40
    /*:
    -0.39
    POSITIVE LOGITS
     Infórmanos
    0.46
    فایل‌لار
    0.42
    NameInMap
    0.40
    mentaux
    0.40
     Exactos
    0.40
     depositphotos
    0.39
    warted
    0.38
    virt
    0.36
     Superhost
    0.36
    チューム
    0.36
    Act Density 0.006%

    No Known Activations