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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    缶
    -0.07
     Evaluate
    -0.07
     Naval
    -0.07
    ace
    -0.07
    鬣
    -0.06
    舸
    -0.06
    เหร
    -0.06
    떰
    -0.06
    荷兰
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    三個
    0.08
    shadow
    0.07
     החו
    0.07
     Sphinx
    0.07
    <<<<<<<<
    0.07
    困
    0.07
     %@
    0.07
     המשתמש
    0.06
    	pw
    0.06
    渗
    0.06
    Act Density 0.006%

    No Known Activations