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

    Neuronpedia

    INDEX
    Explanations

    illard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uzu
    -0.29
    herits
    -0.27
    好äºĨ
    -0.26
    à¸Ĺà¸Ńà¸Ķ
    -0.25
     Muse
    -0.24
     assignable
    -0.24
    æĬĽå¼ĥ
    -0.24
    çļĦä¼ĺçĤ¹
    -0.24
    çĨŁæĤīçļĦ
    -0.24
    inand
    -0.23
    POSITIVE LOGITS
    ivi
    0.31
     Damage
    0.26
    ä¸įåĬ¨
    0.26
    ĥģ
    0.25
     scn
    0.24
     Loose
    0.24
    æķ£
    0.24
    burg
    0.24
    pragma
    0.24
    stroy
    0.24
    Act Density 0.004%

    No Known Activations