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

    Neuronpedia

    INDEX
    Explanations

    output of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਝ
    1.30
    ن
    1.19
    ן
    1.17
    礬
    1.16
    dose
    1.15
    eers
    1.11
     الدراسي
    1.10
     errorCode
    1.05
    як
    1.04
    जिन
    1.03
    POSITIVE LOGITS
     extr
    0.92
    >>>
    0.91
    kw
    0.90
    ket
    0.82
     aches
    0.82
     bloke
    0.82
    omial
    0.81
     Lanc
    0.80
     w
    0.80
     casual
    0.80
    Act Density 0.001%

    No Known Activations