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

    Neuronpedia

    INDEX
    Explanations

    Keep following phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    1.76
    PLY
    1.61
    ్ర
    1.55
    郸
    1.55
    uées
    1.53
     आगमन
    1.41
    cially
    1.40
    larla
    1.40
    ل
    1.40
    부터
    1.38
    POSITIVE LOGITS
    т
    1.86
     homeomorphic
    1.85
     serta
    1.76
    (%
    1.70
     значения
    1.63
     stets
    1.62
     Subsidi
    1.60
     streamwise
    1.57
    ъ
    1.56
     gosh
    1.53
    Act Density 0.107%

    No Known Activations