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

    Neuronpedia

    INDEX
    Explanations

    quotes and excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    好çľĭ
    -0.28
    eenth
    -0.28
     mounts
    -0.28
     loop
    -0.27
    izu
    -0.26
    wat
    -0.26
    .Receive
    -0.25
    wo
    -0.25
     mount
    -0.24
     nett
    -0.24
    POSITIVE LOGITS
    åĽ½éĻħåľ¨çº¿
    0.28
    ималÑĮ
    0.27
    æ³IJ
    0.26
    èĺħ
    0.25
    .isPlaying
    0.25
    restricted
    0.25
    çļĦçĬ¶æĢģ
    0.24
    çī¹æ®Ĭ
    0.24
    æľīåIJį
    0.24
    çī¹æ®ĬæĥħåĨµ
    0.24
    Act Density 0.013%

    No Known Activations