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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anel
    -0.27
    _PUBLIC
    -0.25
    Nick
    -0.25
     classics
    -0.24
    references
    -0.24
    è§ļ
    -0.24
    PTS
    -0.24
    Fear
    -0.24
     anth
    -0.24
    æĶ¹ä¸º
    -0.24
    POSITIVE LOGITS
    èĢĥèĻijåĪ°
    0.29
     obligation
    0.27
    essed
    0.27
    å°¤
    0.26
    履约
    0.25
    å¾ĺå¾Ĭ
    0.24
    ä¸įå¾Ĺä¸į
    0.24
    emente
    0.24
     eventual
    0.24
    éĢīæĭ©äºĨ
    0.24
    Act Density 0.006%

    No Known Activations