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

    Neuronpedia

    INDEX
    Explanations

    refusal and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vell
    0.41
    Blue
    0.39
     হাল
    0.38
     Mach
    0.38
    损
    0.37
     haul
    0.37
     Laund
    0.37
     Lauder
    0.36
    ke
    0.35
    き
    0.35
    POSITIVE LOGITS
    𒌨
    0.46
     convexo
    0.42
    izations
    0.41
    Reasons
    0.40
    Limitations
    0.39
     হইতে
    0.38
    SizePolicy
    0.38
    izarse
    0.38
    રોના
    0.37
    SIMPLE
    0.37
    Act Density 0.036%

    No Known Activations