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

    Neuronpedia

    INDEX
    Explanations

    endearment or endearingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.82
    да
    0.82
    ٥
    0.80
    ນ
    0.77
    <0x98>
    0.76
    سة
    0.73
    ၿ
    0.71
     FIVE
    0.70
    𝔂
    0.70
    ير
    0.70
    POSITIVE LOGITS
    te
    0.70
    ,
    0.70
    zon
    0.66
    os
    0.64
     It
    0.61
    ar
    0.61
    ey
    0.60
    ese
    0.59
    It
    0.59
    on
    0.57
    Act Density 0.000%

    No Known Activations