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

    Neuronpedia

    INDEX
    Explanations

    available to the public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Zb
    0.39
     ascribed
    0.39
     ascertain
    0.38
    šten
    0.38
     unsatisfactory
    0.37
     slog
    0.37
    atrol
    0.37
    指揮
    0.36
    污
    0.36
    Rectangle
    0.36
    POSITIVE LOGITS
     downloadable
    0.66
    开放
    0.55
     доступ
    0.51
     출시
    0.50
     distribu
    0.50
    released
    0.49
     invitación
    0.49
     democrat
    0.49
    开源
    0.49
    ostęp
    0.48
    Act Density 0.193%

    No Known Activations