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

    Neuronpedia

    INDEX
    Explanations

    arithmetic, code, and diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    عرِّف
    0.40
     थोरो
    0.40
    évolution
    0.38
    ূনতম
    0.38
    robespierre
    0.38
    Gosudarstvennyj
    0.37
    உலகின்
    0.37
    اونلو
    0.37
    Metaxy
    0.37
    Melitaea
    0.37
    POSITIVE LOGITS
     B
    0.52
     C
    0.52
     D
    0.48
     A
    0.46
    B
    0.46
     L
    0.45
     Z
    0.45
     N
    0.44
     P
    0.44
    0.44
    Act Density 0.162%

    No Known Activations