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

    Neuronpedia

    INDEX
    Explanations

    dismissed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prophylactic
    0.73
     begint
    0.69
     시작
    0.65
     hooking
    0.65
    起始
    0.63
     preventative
    0.63
     preventiva
    0.62
     triggering
    0.61
    seguir
    0.59
     prophyl
    0.59
    POSITIVE LOGITS
    Dismiss
    0.86
     dismissed
    0.80
     Accordingly
    0.71
     Dismiss
    0.71
    dismiss
    0.69
    Accordingly
    0.68
     merits
    0.66
     disposal
    0.65
     accordingly
    0.64
     disposed
    0.64
    Act Density 0.017%

    No Known Activations