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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cwd
    -0.08
     git
    -0.07
    将近
    -0.07
    _UN
    -0.07
    醋
    -0.07
    npc
    -0.07
    汨
    -0.07
     sustainable
    -0.07
    اصر
    -0.06
    	RT
    -0.06
    POSITIVE LOGITS
    :@""
    0.08
     NEO
    0.08
     Borrow
    0.07
    一艘
    0.07
    hower
    0.07
     Moderate
    0.06
     opposition
    0.06
     Bow
    0.06
    ෆ
    0.06
     Trev
    0.06
    Act Density 0.077%

    No Known Activations