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

    Neuronpedia

    INDEX
    Explanations

    left, right, 2, red, black

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ༔
    0.58
    ฟ
    0.54
    ד
    0.54
    ัล
    0.54
    ร
    0.50
    ה
    0.49
    ל
    0.48
    ༨
    0.47
    ężczy
    0.47
    קי
    0.47
    POSITIVE LOGITS
     also
    0.52
     provides
    0.48
     from
    0.48
     only
    0.47
     with
    0.46
     inoltre
    0.46
     serves
    0.46
     increases
    0.45
     home
    0.45
     Class
    0.45
    Act Density 0.016%

    No Known Activations