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

    Neuronpedia

    INDEX
    Explanations

    Alternative names or synonyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ющему
    0.42
    ுத
    0.39
    izarre
    0.36
    ited
    0.35
    Oh
    0.35
    ួត
    0.34
    orthin
    0.34
    ώ
    0.34
    rimin
    0.34
    EVEN
    0.34
    POSITIVE LOGITS
     también
    0.47
     also
    0.45
     gravy
    0.44
     interchangeably
    0.44
     colloqu
    0.43
     कहें
    0.42
     라고
    0.42
     أيضا
    0.42
     nazy
    0.41
     maize
    0.41
    Act Density 0.157%

    No Known Activations