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

    Neuronpedia

    INDEX
    Explanations

    examples, categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”!
    0.47
    ’!
    0.46
    '!
    0.45
    )!
    0.41
    "!
    0.39
    ''''
    0.34
    .!
    0.34
     {#
    0.34
    ...!
    0.34
    ｛
    0.33
    POSITIVE LOGITS
     zatim
    0.38
     ayrıca
    0.38
     infine
    0.37
     Также
    0.35
     Respondents
    0.34
    緖
    0.34
     perforated
    0.34
     также
    0.34
     trotz
    0.34
    pyridazine
    0.34
    Act Density 0.057%

    No Known Activations