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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to programming and data structures

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

    technical identifiers like stat, err, sort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.50
     nación
    -0.49
     hänen
    -0.45
     mijne
    -0.43
     vedno
    -0.42
     concluye
    -0.42
     Vereinbarung
    -0.42
     isolado
    -0.42
     inoxidable
    -0.41
     jorden
    -0.40
    POSITIVE LOGITS
    uxxxx
    0.60
    UnusedPrivate
    0.59
     ब्रेकडाउन
    0.55
    fjspx
    0.55
     AssemblyProduct
    0.52
     utafitiHapana
    0.52
    舺
    0.51
    aarrggbb
    0.50
    حوالہ
    0.50
     initComponents
    0.48
    Act Density 0.295%

    No Known Activations