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

    Neuronpedia

    INDEX
    Explanations

    tension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     face
    -0.31
     press
    -0.28
     Face
    -0.28
    ersen
    -0.27
    oyo
    -0.26
    ä¸ĭè¡Į
    -0.25
     Press
    -0.25
    -faced
    -0.25
    -route
    -0.25
    èĨº
    -0.25
    POSITIVE LOGITS
    äºĮèĢħ
    0.27
    starter
    0.27
    ç¶ĵé©Ĺ
    0.26
    è±Ĩçĵ£
    0.26
    æıIJè´¨
    0.26
    ä¸įç¦ģ
    0.25
    å´½
    0.25
    åİĨåı²ä¸Ĭ
    0.24
    atica
    0.24
    echa
    0.24
    Act Density 0.590%

    No Known Activations