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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нести
    -0.06
    shouldBe
    -0.06
    love
    -0.06
     iP
    -0.06
    <Player
    -0.06
    ابق
    -0.06
     Schema
    -0.06
    ییر
    -0.06
    .Ag
    -0.06
     Express
    -0.06
    POSITIVE LOGITS
     dirección
    0.07
    _MAC
    0.07
    乘
    0.07
     Fighter
    0.07
    mir
    0.07
     JFK
    0.07
     curl
    0.07
    완
    0.06
     Washington
    0.06
    placements
    0.06
    Act Density 0.083%

    No Known Activations