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

    Neuronpedia

    INDEX
    Explanations

    limit and limitless concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     выбора
    0.42
    য়া
    0.41
     नुकसान
    0.41
    辄
    0.40
     विधाय
    0.40
     DCs
    0.40
    inputSelect
    0.40
    РУ
    0.38
     VIDA
    0.38
     Civilization
    0.38
    POSITIVE LOGITS
    Lim
    0.81
     Lim
    0.80
    lim
    0.77
     lim
    0.69
    estone
    0.61
    itation
    0.59
     LIM
    0.59
     limits
    0.59
    Limite
    0.57
     limiting
    0.55
    Act Density 0.010%

    No Known Activations