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

    Neuronpedia

    INDEX
    Explanations

    approach cautiously, avoid panic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وراق
    0.43
     AKS
    0.43
    ALIAS
    0.42
    CTR
    0.41
    кими
    0.41
    ORGAN
    0.41
     administración
    0.40
    צא
    0.40
     República
    0.40
     Yukarı
    0.40
    POSITIVE LOGITS
     ديك
    0.55
    ियन
    0.54
    iche
    0.54
    adem
    0.52
    idel
    0.50
    aget
    0.49
     funding
    0.49
     арен
    0.48
     রেশন
    0.48
    ases
    0.47
    Act Density 0.000%

    No Known Activations