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

    Neuronpedia

    INDEX
    Explanations

    indicates a consequence or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.70
    7
    0.65
     અને
    0.60
    9
    0.58
    1
    0.56
    6
    0.55
     그래도
    0.54
    Анд
    0.54
    5
    0.54
     जोकि
    0.49
    POSITIVE LOGITS
     också
    0.51
     auch
    0.47
     ook
    0.46
     myös
    0.44
    barkeit
    0.43
    ly
    0.43
     Mga
    0.43
     consequently
    0.41
    者的
    0.41
     tedy
    0.40
    Act Density 0.022%

    No Known Activations