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

    Neuronpedia

    INDEX
    Explanations

    quotations/claims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "Why
    -0.07
    live
    -0.07
     örnek
    -0.06
     Think
    -0.06
     >>↵↵
    -0.06
     tamaño
    -0.06
    .CONT
    -0.06
    -0.06
     Obl
    -0.06
     Cli
    -0.06
    POSITIVE LOGITS
    шей
    0.07
     boarded
    0.07
    .bunifu
    0.06
    XXXX
    0.06
     ž
    0.06
    -j
    0.06
     Alabama
    0.06
     readiness
    0.06
    109
    0.06
    щий
    0.06
    Act Density 0.057%

    No Known Activations