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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     შესახებ
    0.32
    ᕈ
    0.32
    ？」
    0.30
    例子
    0.30
     sprouted
    0.30
     Literal
    0.29
    或其他
    0.29
     êtres
    0.28
     rnorm
    0.28
     предше
    0.28
    POSITIVE LOGITS
     and
    0.94
     आणि
    0.84
     અને
    0.82
     और
    0.80
     và
    0.78
     και
    0.78
    and
    0.73
     и
    0.73
     এবং
    0.72
    และ
    0.67
    Act Density 0.468%

    No Known Activations