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

    Neuronpedia

    INDEX
    Explanations

    difficult emotions or subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ότι
    1.30
    것
    1.27
    ב
    1.25
     difficulties
    1.16
     ਇੱਕ
    1.15
    कर
    1.10
     городах
    1.10
    𝑑
    1.10
     воды
    1.09
    드
    1.09
    POSITIVE LOGITS
    t
    1.49
    is
    1.26
    _
    1.14
    -
    1.10
    ol
    1.01
    ן
    1.00
    us
    0.94
    ist
    0.94
    $
    0.94
    in
    0.91
    Act Density 0.013%

    No Known Activations