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

    Neuronpedia

    INDEX
    Explanations

    Apple Watch backups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kaa
    0.50
    zovaniyu
    0.47
    ikoa
    0.46
     ampio
    0.45
     hém
    0.43
     onda
    0.42
     regola
    0.41
     contradd
    0.41
     élarg
    0.41
    kimi
    0.41
    POSITIVE LOGITS
     pew
    0.42
     பல
    0.40
    SOL
    0.40
     وصلنا
    0.40
     سوال
    0.40
     سؤال
    0.40
     Motivation
    0.39
    无数
    0.39
     الله
    0.39
     solcher
    0.39
    Act Density 0.000%

    No Known Activations