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

    Neuronpedia

    INDEX
    Explanations

    technical systems

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    హ్
    0.48
    nými
    0.46
    äss
    0.46
    śni
    0.46
    ృద్ధి
    0.45
    führen
    0.44
     Ayn
    0.44
    كمال
    0.43
    ého
    0.43
    nyi
    0.43
    POSITIVE LOGITS
     used
    0.51
     options
    0.47
     option
    0.46
     dialogue
    0.44
     over
    0.43
     squire
    0.43
    垨
    0.43
    ওয়ার
    0.42
     enables
    0.41
     forms
    0.41
    Act Density 0.000%

    No Known Activations