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

    Neuronpedia

    INDEX
    Explanations

    a followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kamil
    0.44
     lumière
    0.43
    نیٹ
    0.42
     உறுதி
    0.40
     doubtless
    0.40
    كينا
    0.39
    䜣
    0.39
    కోండి
    0.39
    کین
    0.39
    记住
    0.39
    POSITIVE LOGITS
    blest
    0.40
     extensions
    0.39
     transferable
    0.39
     room
    0.38
     sala
    0.38
     each
    0.36
     euro
    0.36
     dollars
    0.36
    isf
    0.36
     extension
    0.36
    Act Density 0.001%

    No Known Activations