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

    Neuronpedia

    INDEX
    Explanations

    Desire, determination, improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æŶæĬ¥
    -0.26
    æ¡Įä¸Ĭ
    -0.25
     gloves
    -0.25
    çļĦçľ¼
    -0.25
    å¼¼
    -0.24
    -Clause
    -0.24
     Kenn
    -0.23
     Larson
    -0.23
    (sample
    -0.23
    çĶ«
    -0.23
    POSITIVE LOGITS
    åıĪ
    0.29
    åıĪèĥ½
    0.29
    orte
    0.29
    对äºİæĪij们
    0.26
    éĩijæ²Ļ
    0.25
     ours
    0.25
     nowhere
    0.25
    name
    0.24
    orts
    0.24
     parch
    0.24
    Act Density 0.014%

    No Known Activations