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

    Neuronpedia

    INDEX
    Explanations

    instances of square brackets

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

    code structure and data access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.61
    ymce
    -0.53
     aérea
    -0.53
     ujednoznacz
    -0.52
     Turquía
    -0.52
    InputBorder
    -0.51
     Eccl
    -0.49
     RIPRODUZIONE
    -0.49
    ')){
    -0.49
     exemplaire
    -0.48
    POSITIVE LOGITS
    ["
    1.80
     ["
    1.31
    (["
    1.26
    =["
    1.09
    ]["
    1.01
    {"
    0.96
    (“
    0.88
    ["_
    0.84
    ({"
    0.84
    ("
    0.84
    Act Density 0.008%

    No Known Activations