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

    Neuronpedia

    INDEX
    Explanations

    removing filters and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🫶
    0.56
    🥹
    0.56
    🫣
    0.54
    🫢
    0.53
    十四
    0.50
    🫠
    0.46
     XXII
    0.46
    二十
    0.45
     XXIV
    0.45
    🫡
    0.44
    POSITIVE LOGITS
    aithe
    0.40
    iftet
    0.39
     tightening
    0.39
     банки
    0.39
     బ్యాంకు
    0.37
     wicht
    0.37
     sweeteners
    0.36
    bordered
    0.36
     lifts
    0.36
     Arthritis
    0.35
    Act Density 0.002%

    No Known Activations