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

    Neuronpedia

    INDEX
    Explanations

    ships being launched

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACP
    -0.30
    ewater
    -0.27
    ç»´å¥ĩ
    -0.27
    usher
    -0.26
    è²´
    -0.25
    OwnProperty
    -0.25
    esome
    -0.25
    uali
    -0.25
    éľĩåĬ¨
    -0.25
    SSIP
    -0.25
    POSITIVE LOGITS
    ambre
    0.28
    é¢ĵ
    0.28
    ¬ģ
    0.27
    åĪ¨
    0.27
    éĢĢ
    0.25
     px
    0.25
     Hoe
    0.25
    æ½¼
    0.24
    ille
    0.24
     withhold
    0.24
    Act Density 0.046%

    No Known Activations