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

    Neuronpedia

    INDEX
    Explanations

    GUI widgets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dictionary
    -0.07
    lt
    -0.06
    แต
    -0.06
    loy
    -0.06
    ircon
    -0.06
    foot
    -0.06
    vi
    -0.06
    تضمن
    -0.06
    污泥
    -0.06
     اختيار
    -0.06
    POSITIVE LOGITS
    岽
    0.08
     FORWARD
    0.08
    	Common
    0.08
    �
    0.07
    能使
    0.07
    公共文化
    0.07
    ----------↵
    0.07
    좀
    0.07
    caler
    0.07
    就觉得
    0.07
    Act Density 0.026%

    No Known Activations