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

    Neuronpedia

    INDEX
    Explanations

    lettuce in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     condivid
    0.50
     kanske
    0.46
    之事
    0.46
     invests
    0.42
    khart
    0.41
     chose
    0.41
    ق
    0.41
    ativi
    0.41
     برخی
    0.41
     verwij
    0.41
    POSITIVE LOGITS
     That
    0.41
    髏
    0.38
    욱
    0.36
    ✿
    0.35
     Ско
    0.35
     それ
    0.35
    λ
    0.35
     Che
    0.34
     ).
    0.34
    ).^
    0.33
    Act Density 0.000%

    No Known Activations