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

    Neuronpedia

    INDEX
    Explanations

    starting from scratch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Silk
    0.44
     Trans
    0.42
     trans
    0.42
     Be
    0.42
    asing
    0.42
    otrans
    0.40
     gr
    0.40
    hap
    0.39
    飽
    0.38
     I
    0.38
    POSITIVE LOGITS
    蟀
    0.45
    デニム
    0.43
    भंगा
    0.42
    ଙ
    0.42
     жүктөө
    0.41
    🕓
    0.41
    caya
    0.41
    怎么样
    0.41
    旅游
    0.40
    िडेट
    0.40
    Act Density 0.000%

    No Known Activations