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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èĥ½çľĭåĪ°
    -0.28
    æij¸
    -0.27
    uje
    -0.27
     about
    -0.26
    综
    -0.26
    éĢıè§Ĩ
    -0.26
    亮
    -0.26
     certify
    -0.25
    éĢļ
    -0.25
     confirm
    -0.25
    POSITIVE LOGITS
    eprom
    0.28
    holders
    0.25
    æŃ¥ä¼IJ
    0.24
    ãĤĭãĤĪãģĨãģ«
    0.23
    andin
    0.23
    使ä¹ĭ
    0.23
    ãģĬãĤĬ
    0.23
    engo
    0.23
    館
    0.23
    PWM
    0.23
    Act Density 0.061%

    No Known Activations