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

    Neuronpedia

    INDEX
    Explanations

    alone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ultimately
    -0.07
    Overview
    -0.06
     slideshow
    -0.06
    (relative
    -0.06
    _pic
    -0.06
     VALID
    -0.06
    잡담
    -0.06
     baby
    -0.06
     рекоменду
    -0.06
     Gale
    -0.06
    POSITIVE LOGITS
    -results
    0.07
     Ver
    0.06
    ��
    0.06
    "https
    0.06
     tel
    0.06
    제
    0.06
     disput
    0.06
    rich
    0.06
    行動
    0.06
    巨
    0.06
    Act Density 0.016%

    No Known Activations