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

    Neuronpedia

    INDEX
    Explanations

    Japanese and Korean adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     existem
    0.87
     berper
    0.85
     trái
    0.85
     têm
    0.83
     않는다
    0.82
    ள்ளது
    0.81
    는다
    0.81
     한다
    0.81
     있습니다
    0.79
     ৯
    0.79
    POSITIVE LOGITS
    ness
    1.06
    くて
    1.06
    く
    1.00
    eness
    0.96
    さを
    0.95
    set
    0.95
    な
    0.94
    하게
    0.92
    Telemetry
    0.91
    한
    0.89
    Act Density 0.063%

    No Known Activations