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

    Neuronpedia

    INDEX
    Explanations

    looks like having

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ().
    0.20
     を
    0.20
     WITH
    0.19
     これらの
    0.18
    使用
    0.18
     INCLUDING
    0.18
     使用
    0.17
    ；
    0.17
     Với
    0.17
    との
    0.17
    POSITIVE LOGITS
     irrever
    0.24
     cynical
    0.23
     arrogant
    0.22
     aloof
    0.22
     uneasy
    0.22
     idealistic
    0.22
     melanch
    0.21
     convivial
    0.21
     defiance
    0.21
     akin
    0.20
    Act Density 5.287%

    No Known Activations