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

    Neuronpedia

    INDEX
    Explanations

    the followed by diverse nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.63
    te
    0.62
     And
    0.55
    𝟐
    0.54
    ות
    0.54
    2
    0.54
    and
    0.53
    ed
    0.51
    vár
    0.51
    anden
    0.51
    POSITIVE LOGITS
    س
    0.63
    ن
    0.63
    ス
    0.61
    ます
    0.60
    ン
    0.60
    ד
    0.60
     to
    0.59
     sebagainya
    0.58
     recomendable
    0.56
    {
    0.54
    Act Density 0.119%

    No Known Activations