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

    Neuronpedia

    INDEX
    Explanations

    synthetic attempts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🍇
    0.39
     LTC
    0.38
     thị
    0.37
     αυ
    0.36
    Charm
    0.36
    വൃ
    0.36
    隔
    0.36
    Let
    0.36
    abe
    0.35
    Au
    0.35
    POSITIVE LOGITS
     GIL
    0.53
    ouflage
    0.43
    วัสดี
    0.41
     QuantityOnHand
    0.41
    flowLayoutPanel
    0.39
    ੋ
    0.39
    ッドレス
    0.38
    হাব
    0.38
     crust
    0.38
     oblivious
    0.38
    Act Density 0.000%

    No Known Activations