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

    Neuronpedia

    INDEX
    Explanations

    through small openings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NM
    0.40
     Tiny
    0.39
    Tiny
    0.38
     ngữ
    0.37
     H
    0.36
     Empty
    0.36
     Examine
    0.35
     probably
    0.35
    tiny
    0.35
     Promised
    0.35
    POSITIVE LOGITS
    ಸ್ತಕ
    0.53
    iseite
    0.46
     المثلثيه
    0.44
    anbul
    0.42
    귿
    0.42
     hote
    0.41
    ὦ
    0.41
    เภอ
    0.41
    ذاء
    0.41
    zysz
    0.40
    Act Density 0.000%

    No Known Activations