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

    Neuronpedia

    INDEX
    Explanations

    Yes/Jaor$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brando
    0.41
    Orth
    0.39
    Talk
    0.38
     TLabel
    0.37
    דר
    0.37
    സ്തു
    0.37
    eqref
    0.36
    墨
    0.36
    Sho
    0.35
    Domain
    0.35
    POSITIVE LOGITS
     self
    0.42
     Self
    0.37
    自
    0.37
    ưng
    0.36
     محر
    0.35
     enzymatic
    0.35
     NGS
    0.35
     само
    0.34
     catalytic
    0.34
    })-\
    0.33
    Act Density 0.000%

    No Known Activations