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

    Neuronpedia

    INDEX
    Explanations

    generates previously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ையை
    0.42
    лен
    0.39
    номет
    0.39
     espírito
    0.38
    lename
    0.38
     Beim
    0.38
    odigd
    0.38
     लघु
    0.37
    ൈ
    0.37
     Pareto
    0.36
    POSITIVE LOGITS
    Gorgeous
    0.44
    வதேச
    0.42
    Kell
    0.41
    สวย
    0.40
    Instr
    0.40
    द्दीन
    0.39
    的设计
    0.38
    ROWN
    0.38
     dior
    0.38
    BOLD
    0.37
    Act Density 0.002%

    No Known Activations