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

    Neuronpedia

    INDEX
    Explanations

    European languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     countless
    0.80
     प्रत्येक
    0.79
     tirelessly
    0.77
     boyunca
    0.77
     mampu
    0.77
     cabinetry
    0.76
     berfungsi
    0.75
     homeostasis
    0.73
    を中心に
    0.73
     recuperação
    0.72
    POSITIVE LOGITS
    。
    0.83
    us
    0.77
     typos
    0.66
    ！
    0.65
    }$
    0.65
    })
    0.64
    Mario
    0.64
    ）
    0.63
    junctive
    0.63
    Ь
    0.63
    Act Density 3.739%

    No Known Activations