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

    Neuronpedia

    INDEX
    Explanations

    elastic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illis
    -0.08
    -year
    -0.07
     Conse
    -0.07
    可能です
    -0.07
    .ep
    -0.07
    ˆ
    -0.07
    ﭴ
    -0.07
     flags
    -0.07
    מרי
    -0.07
    Ŭ
    -0.07
    POSITIVE LOGITS
     Invisible
    0.08
     pathetic
    0.07
     embrace
    0.07
     ник
    0.07
    "]);↵
    0.07
     plywood
    0.07
     Irma
    0.07
     bamboo
    0.07
    襄阳
    0.07
     wound
    0.07
    Act Density 0.005%

    No Known Activations