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

    Neuronpedia

    INDEX
    Explanations

    terms of options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tamp
    0.71
     Etat
    0.70
     sellest
    0.70
    rolysis
    0.69
     variously
    0.67
    ⋱
    0.67
     investi
    0.67
     ಸೇರಿದ
    0.66
    先后
    0.66
    vgili
    0.66
    POSITIVE LOGITS
     kinks
    0.88
     사이즈
    0.87
     habilidades
    0.85
     perks
    0.80
    解析
    0.79
     multitasking
    0.79
     benchmarks
    0.79
     sacrifices
    0.78
     socializing
    0.77
     streamlining
    0.76
    Act Density 0.001%

    No Known Activations