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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nosis
    -0.07
     Ort
    -0.07
    ǭ
    -0.07
    材料
    -0.06
     watershed
    -0.06
     neuroscience
    -0.06
     dumps
    -0.06
     isValid
    -0.06
    巅
    -0.06
    clado
    -0.06
    POSITIVE LOGITS
    Square
    0.07
     jouer
    0.07
    手游
    0.07
    prefix
    0.06
    	GUI
    0.06
    �
    0.06
    演出
    0.06
    ];↵
    0.06
    _Free
    0.06
    Cha
    0.06
    Act Density 0.012%

    No Known Activations