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

    Neuronpedia

    INDEX
    Explanations

    scientific language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     since
    -0.06
     thân
    -0.06
    .pick
    -0.06
     ck
    -0.06
    กล
    -0.06
     glass
    -0.06
     kli
    -0.06
    圳
    -0.06
     Registrar
    -0.06
     udp
    -0.06
    POSITIVE LOGITS
    ==(
    0.07
    (hidden
    0.07
    #####
    0.07
    argout
    0.07
    _vector
    0.07
     innoc
    0.06
    !("
    0.06
     MACHINE
    0.06
     qreal
    0.06
    LOWER
    0.06
    Act Density 0.244%

    No Known Activations