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

    Neuronpedia

    INDEX
    Explanations

    Go functions and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लिरिक्स
    0.44
    ﯼ
    0.43
     Voters
    0.41
     deur
    0.40
     Déf
    0.39
    '";
    0.38
     Metast
    0.38
     Minority
    0.37
     pédicule
    0.37
    ావ
    0.37
    POSITIVE LOGITS
    funk
    0.48
    preview
    0.45
    linear
    0.44
    Funk
    0.43
    func
    0.43
    Cairo
    0.43
    Ed
    0.43
    lable
    0.41
    こな
    0.40
    VILLE
    0.40
    Act Density 0.000%

    No Known Activations