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

    Neuronpedia

    INDEX
    Explanations

    Tumblr or consulting firm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necrosis
    1.05
    ാൽ
    1.01
    lık
    0.98
     Dae
    0.94
    Loksatta
    0.94
     Sharjah
    0.93
    iotic
    0.93
     Dhar
    0.93
    зде
    0.92
    caling
    0.91
    POSITIVE LOGITS
    쯤
    0.85
    行った
    0.77
    ive
    0.73
    तील
    0.73
    )
    0.72
    이랑
    0.70
     giurid
    0.70
     го
    0.69
    婦
    0.69
    的一個
    0.68
    Act Density 0.000%

    No Known Activations