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

    Neuronpedia

    INDEX
    Explanations

    legal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiger
    -0.07
     tới
    -0.07
    okud
    -0.06
     negativity
    -0.06
    canvas
    -0.06
    Light
    -0.06
    .pat
    -0.06
     JACK
    -0.06
    _STORAGE
    -0.06
    _income
    -0.06
    POSITIVE LOGITS
    Attend
    0.07
     enumerator
    0.06
     dated
    0.06
     Args
    0.06
    ۱۳۸
    0.06
     sque
    0.06
     hf
    0.06
     시행
    0.06
    	  ↵
    0.06
     탈
    0.06
    Act Density 0.039%

    No Known Activations