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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وث
    -0.07
     réseau
    -0.07
    ців
    -0.07
    _pkg
    -0.07
    Ops
    -0.06
     Ты
    -0.06
    stab
    -0.06
     Chad
    -0.06
     StartTime
    -0.06
     [[
    -0.06
    POSITIVE LOGITS
    `↵
    0.06
    ρκε
    0.06
     ACTION
    0.06
     vitro
    0.06
     vapor
    0.06
    .Item
    0.06
    ubishi
    0.06
    ové
    0.06
    "The
    0.06
    "M
    0.06
    Act Density 0.008%

    No Known Activations