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

    Neuronpedia

    INDEX
    Explanations

    last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slice
    -0.07
        		↵
    -0.06
     الأك
    -0.06
    ニニ
    -0.06
    /settingsdialog
    -0.06
     equality
    -0.06
     essentials
    -0.06
    utors
    -0.06
     bleiben
    -0.06
    fila
    -0.06
    POSITIVE LOGITS
     Maiden
    0.07
     अद
    0.07
    caught
    0.07
    yards
    0.07
     sca
    0.06
     تغییر
    0.06
     Pee
    0.06
    felt
    0.06
     су
    0.06
     Hond
    0.06
    Act Density 0.015%

    No Known Activations