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

    Neuronpedia

    INDEX
    Explanations

    reduction/negatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸ĢæŦ
    -0.33
    å¦ĤæѤ
    -0.26
    QE
    -0.26
    anked
    -0.26
    ?',
    -0.25
    è¿Ļæł·
    -0.25
     Oakland
    -0.25
    ?")↵
    -0.24
     eBooks
    -0.24
    éĽħæĢĿ
    -0.24
    POSITIVE LOGITS
    æŀģ
    0.28
     trade
    0.27
    磶
    0.27
    为é¦ĸçļĦ
    0.26
    rig
    0.25
     minus
    0.25
    0.25
     plus
    0.24
    å¥ĭæĸĹ缮æłĩ
    0.24
     rural
    0.24
    Act Density 0.004%

    No Known Activations