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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    กำหนด
    -0.07
    Б
    -0.07
    ITY
    -0.07
    เคย
    -0.07
    940
    -0.06
    (Be
    -0.06
     BU
    -0.06
     threatened
    -0.06
     Montgomery
    -0.06
    bour
    -0.06
    POSITIVE LOGITS
    .CLIENT
    0.07
     dips
    0.07
    .Mod
    0.07
    entre
    0.06
    aises
    0.06
    Sept
    0.06
     Пет
    0.06
     Populate
    0.06
    ERVER
    0.06
     wanna
    0.06
    Act Density 0.321%

    No Known Activations