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

    Neuronpedia

    INDEX
    Explanations

    guest or WiFi access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    深刻
    0.42
    挂
    0.41
    霞
    0.40
    议
    0.39
    砲
    0.38
     Hanging
    0.37
    ኬ
    0.37
    縮
    0.35
    ก็ตาม
    0.35
    ния
    0.35
    POSITIVE LOGITS
     spruce
    0.46
     attest
    0.44
     apreci
    0.44
     absorbs
    0.42
     cosmet
    0.41
     ciel
    0.40
     beeh
    0.40
     checkers
    0.40
     estrange
    0.40
     absorbent
    0.39
    Act Density 0.000%

    No Known Activations