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

    Neuronpedia

    INDEX
    Explanations

    often more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ailes
    0.42
    dessous
    0.41
    ูด
    0.39
    Subset
    0.39
    👹
    0.39
    依据
    0.39
     moveTo
    0.38
     transfert
    0.37
    实
    0.37
    定義
    0.37
    POSITIVE LOGITS
     Chiu
    0.49
     chum
    0.41
    cX
    0.38
     long
    0.36
     chuck
    0.35
    kken
    0.35
     prickly
    0.35
     Kanye
    0.35
    croll
    0.35
     disappointing
    0.34
    Act Density 0.000%

    No Known Activations