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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components and their properties

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

    Code-related strings and variable names

    np_acts-logits-general · gemini-2.0-flash

    programming terms and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lap
    -0.48
    ("$.
    -0.43
    ru
    -0.42
     unter
    -0.41
    assan
    -0.41
    uste
    -0.41
     dar
    -0.40
     ri
    -0.40
     Ribeiro
    -0.40
    rib
    -0.40
    POSITIVE LOGITS
    InitVars
    0.98
    ↵↵↵↵↵↵↵↵↵↵
    0.85
    ↵↵↵↵↵↵↵↵
    0.84
     مشين
    0.83
    ↵↵↵↵↵↵
    0.83
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.81
     initComponents
    0.80
    ↵↵↵↵↵↵↵↵↵↵↵
    0.80
    ↵↵↵↵↵↵↵
    0.80
    Act Density 0.130%

    No Known Activations