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

    Neuronpedia

    INDEX
    Explanations

    machine learning and foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     οποίο
    0.41
    ），
    0.38
    epsilon
    0.36
    F
    0.36
    க்
    0.35
    )，
    0.35
    _
    0.35
    କ
    0.34
    0.33
    ）。
    0.33
    POSITIVE LOGITS
     queda
    0.41
     Führ
    0.37
     fazer
    0.36
     zeal
    0.36
     seguir
    0.36
     zur
    0.35
     Shabd
    0.35
     Kategor
    0.35
     jef
    0.35
     tumult
    0.35
    Act Density 0.145%

    No Known Activations