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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ycopg
    -0.07
    ്�
    -0.07
    unks
    -0.06
     THIS
    -0.06
     Salem
    -0.06
     this
    -0.06
     Taco
    -0.06
    ให
    -0.06
     Các
    -0.06
     کو
    -0.06
    POSITIVE LOGITS
     الحي
    0.06
     Preference
    0.06
     slaughter
    0.06
     Stewart
    0.06
     southeastern
    0.06
    sign
    0.06
     ;;↵
    0.06
    ]].
    0.06
    basket
    0.06
     Muss
    0.06
    Act Density 0.021%

    No Known Activations