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

    Neuronpedia

    INDEX
    Explanations

    Space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inner
    -0.26
    inaire
    -0.26
     Tone
    -0.26
    çģ¯
    -0.25
    wind
    -0.25
    issant
    -0.25
     race
    -0.25
    (filter
    -0.24
    å¼ĢçĿĢ
    -0.24
    edException
    -0.24
    POSITIVE LOGITS
    éĴī
    0.28
    ä¸ĺ
    0.28
    cken
    0.27
     thÃŃ
    0.27
     scout
    0.27
    çĭ¬
    0.27
    bern
    0.26
    JSONObject
    0.26
    å¤ĸåĽ½è¯Ń
    0.26
    ForMember
    0.25
    Act Density 0.039%

    No Known Activations