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

    Neuronpedia

    INDEX
    Explanations

    ways to or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intensively
    0.84
     extensively
    0.81
    한테
    0.80
     warmly
    0.79
     fortemente
    0.78
     vigorously
    0.78
     وغیرہ
    0.77
     harshly
    0.77
     대상으로
    0.77
     lightly
    0.75
    POSITIVE LOGITS
     whereby
    0.95
     wherein
    0.87
    ในการ
    0.74
     umożliw
    0.74
    orship
    0.74
     exists
    0.71
     umož
    0.70
     bagaimana
    0.69
    External
    0.68
     toward
    0.68
    Act Density 0.444%

    No Known Activations