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

    Neuronpedia

    INDEX
    Explanations

    setting object parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وما
    0.45
    What
    0.40
     STEP
    0.39
    越來越
    0.38
     keuze
    0.37
     ceea
    0.37
     anhand
    0.37
     وب
    0.36
    Replacement
    0.36
     و
    0.36
    POSITIVE LOGITS
     setattr
    0.49
     renamed
    0.49
    disable
    0.48
     renaming
    0.46
     rename
    0.45
     set
    0.44
    idu
    0.44
     设置
    0.43
     setDefault
    0.43
    setlength
    0.43
    Act Density 0.075%

    No Known Activations