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

    Neuronpedia

    INDEX
    Explanations

    adding something else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.68
    ع
    0.68
    ע
    0.63
    に
    0.61
    ใน
    0.59
    การ
    0.56
    Dubai
    0.56
    で
    0.55
     ở
    0.54
    从
    0.54
    POSITIVE LOGITS
     necessitates
    0.57
     nécessite
    0.55
    носит
    0.53
     generates
    0.52
     occurs
    0.52
     relies
    0.52
     exudes
    0.51
     extravaganza
    0.51
     alleges
    0.50
     delights
    0.50
    Act Density 0.000%

    No Known Activations