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

    Neuronpedia

    INDEX
    Explanations

    generating canvas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageNow
    0.38
    哩
    0.38
    鼠
    0.37
     tireless
    0.36
    حدث
    0.35
     Mandalorian
    0.34
    pecial
    0.34
    पती
    0.34
     traduire
    0.34
     interpreter
    0.34
    POSITIVE LOGITS
     об
    0.45
    чении
    0.42
     wymaga
    0.42
     Об
    0.41
     pg
    0.41
     abge
    0.41
     бө
    0.41
     Ob
    0.40
    ഴ
    0.40
     разре
    0.40
    Act Density 0.000%

    No Known Activations