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

    Neuronpedia

    INDEX
    Explanations

    begin sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.48
    er
    0.42
     ও
    0.41
    imde
    0.36
    ov
    0.35
    ’
    0.35
     בת
    0.35
    imą
    0.35
    že
    0.34
     practitioner
    0.34
    POSITIVE LOGITS
    ال
    0.52
    {
    0.47
    \
    0.43
    غ
    0.42
     ошиб
    0.40
     méxico
    0.39
    ILL
    0.38
    ートン
    0.38
    ート
    0.38
    лайн
    0.38
    Act Density 0.000%

    No Known Activations