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

    Neuronpedia

    INDEX
    Explanations

    phrases involving together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.47
    ﺖ
    0.42
    和
    0.41
    کر
    0.40
    ﺮ
    0.40
    ス
    0.38
    我
    0.37
     svoje
    0.36
    ्स
    0.36
     odgovor
    0.36
    POSITIVE LOGITS
    ad
    0.49
    il
    0.44
    li
    0.40
    la
    0.36
    ant
    0.35
    isit
    0.34
    r
    0.34
    le
    0.33
    æ
    0.33
    iskt
    0.33
    Act Density 0.058%

    No Known Activations