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

    Neuronpedia

    INDEX
    Explanations

    results or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ከተ
    0.38
     REGIUNI
    0.38
    Rigidbody
    0.36
    য়
    0.34
    Chand
    0.33
    峎
    0.33
    য়াদ
    0.33
    这是一个
    0.32
     {}
    0.32
     başlayalım
    0.32
    POSITIVE LOGITS
     consequently
    2.64
    Consequently
    2.61
     Consequently
    2.59
    因此
    2.06
    因而
    2.02
     consequence
    1.89
     therefore
    1.88
     conséquence
    1.85
     consecuencia
    1.77
     dadurch
    1.77
    Act Density 0.034%

    No Known Activations