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

    Neuronpedia

    INDEX
    Explanations

    difficulty, pressure, exertion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    1.48
    is
    1.45
    ли
    1.41
    ческих
    1.36
    to
    1.30
    were
    1.28
    ون
    1.22
    ся
    1.21
    ties
    1.21
    t
    1.19
    POSITIVE LOGITS
    I
    1.54
    N
    1.43
    T
    1.33
    اية
    1.23
     выпол
    1.16
    و
    1.14
    O
    1.13
    R
    1.10
    kách
    1.05
          
    1.04
    Act Density 0.208%

    No Known Activations