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

    Neuronpedia

    INDEX
    Explanations

    specific area, optimal level, universo observable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    netfx
    0.40
     ইমরান
    0.38
    ush
    0.37
    tfrac
    0.37
    []}
    0.37
    WG
    0.37
     Perez
    0.36
    alg
    0.36
     ப்ர
    0.36
    frac
    0.35
    POSITIVE LOGITS
    ќ
    0.47
     \\..
    0.42
                            
    0.41
     »
    0.41
     शीर्षक
    0.40
     soles
    0.39
    ..?
    0.39
    楫
    0.39
    伙
    0.38
     Mỗi
    0.38
    Act Density 0.000%

    No Known Activations