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

    Neuronpedia

    INDEX
    Explanations

    or, and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    电视
    -0.07
     Muk
    -0.06
     ابتدا
    -0.06
    219
    -0.06
     Terrace
    -0.06
     bored
    -0.06
    ()],↵
    -0.06
    }.↵
    -0.06
     metavar
    -0.06
     [:
    -0.06
    POSITIVE LOGITS
    :UIControlState
    0.07
    sburgh
    0.07
    entic
    0.07
    wayne
    0.06
     dục
    0.06
     خط
    0.06
     велич
    0.06
     sendo
    0.06
     Summon
    0.06
    isme
    0.06
    Act Density 0.099%

    No Known Activations