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

    Neuronpedia

    INDEX
    Explanations

    What is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    姏
    0.42
    🥨
    0.42
    formats
    0.40
     entière
    0.39
    awsze
    0.39
    ző
    0.38
     Facilities
    0.38
     avantages
    0.38
    łości
    0.38
    dpy
    0.38
    POSITIVE LOGITS
     =
    0.41
    ='
    0.38
     Lem
    0.38
    public
    0.37
    Vi
    0.37
    Lem
    0.37
    Λ
    0.37
    Title
    0.36
    Lemon
    0.36
    Ed
    0.36
    Act Density 0.000%

    No Known Activations