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

    Neuronpedia

    INDEX
    Explanations

    things become exhausting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    నే
    0.50
    河流
    0.48
    ूथ
    0.48
    indazole
    0.47
     gonflement
    0.46
    茘
    0.46
     elucidation
    0.45
    놁
    0.45
    关节
    0.45
     효과
    0.45
    POSITIVE LOGITS
    when
    0.62
     when
    0.55
    od
    0.53
     When
    0.53
    os
    0.52
    it
    0.52
    where
    0.51
    if
    0.51
    za
    0.50
    c
    0.49
    Act Density 0.007%

    No Known Activations