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

    Neuronpedia

    INDEX
    Explanations

    transport or neurons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ín
    0.53
     painful
    0.45
    man
    0.44
    loem
    0.42
    ínt
    0.41
    í
    0.40
    ь
    0.40
    mujer
    0.40
    inand
    0.39
    抵抗
    0.39
    POSITIVE LOGITS
     QuantityOnHand
    0.54
    \,.
    0.48
     რაც
    0.47
    дыду
    0.45
    ोरा
    0.45
    ,_-
    0.44
     专业
    0.44
    dı
    0.44
     گئی
    0.43
     Tipps
    0.43
    Act Density 0.003%

    No Known Activations