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

    Neuronpedia

    INDEX
    Explanations

    Stockholm, GWD Minden, Vikarsjö, plugins, modern, gritty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पाठ
    0.43
    पाठ
    0.41
    ORDON
    0.40
    ື່
    0.37
     Calls
    0.37
    calls
    0.37
     отправи
    0.37
    JAV
    0.37
    platinum
    0.37
     kön
    0.37
    POSITIVE LOGITS
    IK
    0.56
     IK
    0.45
    IB
    0.45
     Mull
    0.41
     IB
    0.41
    IF
    0.39
     Pix
    0.38
     Tran
    0.38
     Mule
    0.38
    iset
    0.38
    Act Density 0.002%

    No Known Activations