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

    Neuronpedia

    INDEX
    Explanations

    function declarations in code

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

    function declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.84
    Vidite
    -0.75
     '\\;'
    -0.70
     poffible
    -0.69
    цездатний
    -0.66
     otomatig
    -0.66
    MENAFN
    -0.64
    ſelves
    -0.64
    ſelf
    -0.64
    ロウィン
    -0.64
    POSITIVE LOGITS
     initComponents
    0.50
     the
    0.49
    The
    0.45
     The
    0.45
    setupUi
    0.41
    ↵
    0.41
    ↵↵
    0.40
     
    0.40
    an
    0.35
    function
    0.34
    Act Density 0.001%

    No Known Activations