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

    Neuronpedia

    INDEX
    Explanations

    actions and verbs associated with doing or performing tasks

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

    forms of do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.52
     laaj
    -0.44
    wikkel
    -0.41
    ihnach
    -0.40
    ikka
    -0.40
    ücksich
    -0.39
    acidade
    -0.39
    aima
    -0.39
     segnal
    -0.39
     epä
    -0.38
    POSITIVE LOGITS
     bParam
    0.54
     Happens
    0.54
     AssemblyProduct
    0.50
    RTLD
    0.50
     роботи
    0.49
     doings
    0.49
     AssemblyCulture
    0.49
    happens
    0.47
     iParam
    0.46
    happen
    0.46
    Act Density 0.012%

    No Known Activations