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

    Neuronpedia

    INDEX
    Explanations

    high-frequency programming or technical keywords and terms

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

    common English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.92
    SourceChecksum
    -0.68
    الدراسه
    -0.67
    fjspx
    -0.64
     estekak
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    ="@+
    -0.60
    MemoryWarning
    -0.60
    Autoritní
    -0.60
    principalColumn
    -0.60
    POSITIVE LOGITS
     the
    0.50
    The
    0.40
     The
    0.39
     simply
    0.38
     It
    0.37
     Dés
    0.36
     FontWeight
    0.36
     rem
    0.36
     élé
    0.35
    It
    0.35
    Act Density 0.118%

    No Known Activations