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

    Neuronpedia

    INDEX
    Explanations

    e.g. for examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eing
    0.42
    ́
    0.41
    ::~
    0.41
     。,
    0.37
    ():
    0.37
    </h3>
    0.36
    ೕ
    0.36
    zione
    0.36
    cionario
    0.36
    रोग
    0.36
    POSITIVE LOGITS
     Examples
    0.59
     example
    0.57
     eg
    0.54
     examples
    0.53
     bijvoorbeeld
    0.53
    比如说
    0.53
    Examples
    0.53
    比如說
    0.53
     Example
    0.52
     esempio
    0.52
    Act Density 0.244%

    No Known Activations