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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .visual
    -0.07
     dati
    -0.07
    全套
    -0.07
    (table
    -0.07
    Blue
    -0.06
     cleric
    -0.06
     euth
    -0.06
    两只
    -0.06
     copying
    -0.06
     Crash
    -0.06
    POSITIVE LOGITS
     sæ
    0.07
    /=
    0.07
    ogy
    0.06
    🎹
    0.06
    奠
    0.06
     постоян
    0.06
    фан
    0.06
    かな
    0.06
     Soldiers
    0.06
     gubern
    0.06
    Act Density 0.000%

    No Known Activations