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

    Neuronpedia

    INDEX
    Explanations

    phrases marked by "so-called"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    0.89
     способом
    0.81
     şekilde
    0.77
    )”.
    0.76
     Faun
    0.76
    किशोर
    0.75
     جميع
    0.74
    siniz
    0.73
    ],
    0.71
    狒
    0.71
    POSITIVE LOGITS
    t
    1.00
    j
    0.98
    m
    0.95
    n
    0.89
    he
    0.84
    en
    0.80
    ing
    0.80
    el
    0.79
    q
    0.79
    v
    0.79
    Act Density 0.000%

    No Known Activations