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

    Neuronpedia

    INDEX
    Explanations

    Blinder, Zeman, Houghton, Ganse, Pauly, Skyler, Kelemen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /
    0.55
    /
    0.52
    ↵
    0.51
     (
    0.50
     ca
    0.50
     ist
    0.50
     t
    0.49
     g
    0.49
     est
    0.48
     de
    0.48
    POSITIVE LOGITS
    eredith
    0.55
    ileen
    0.49
    躹
    0.47
    㓦
    0.46
    entieth
    0.45
     इंट्रोडक्शन
    0.45
    جموعة
    0.44
    訒
    0.44
    兟
    0.44
    呥
    0.44
    Act Density 0.047%

    No Known Activations