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

    Neuronpedia

    INDEX
    Explanations

    uncompromising performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रचंड
    0.43
    Wearing
    0.40
     વસ્તુ
    0.38
    wearing
    0.38
     هذه
    0.38
    affaire
    0.38
    ่
    0.38
    礁
    0.38
    thing
    0.37
    แด
    0.37
    POSITIVE LOGITS
     vd
    0.43
     expon
    0.42
    etro
    0.41
     leuk
    0.41
     Omb
    0.41
     companies
    0.40
     vanguard
    0.39
     viy
    0.39
     VU
    0.39
    ikala
    0.39
    Act Density 0.000%

    No Known Activations