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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .closed
    -0.07
    /S
    -0.06
     invis
    -0.06
     Chester
    -0.06
    θενής
    -0.06
    /",↵
    -0.06
     gross
    -0.06
    ERTICAL
    -0.06
    >)↵
    -0.06
    getPath
    -0.06
    POSITIVE LOGITS
    Fashion
    0.07
    ardown
    0.06
     سو
    0.06
     erotique
    0.06
     bx
    0.06
    уди
    0.06
    هه
    0.06
     Mojo
    0.06
     engr
    0.06
     rospy
    0.06
    Act Density 0.036%

    No Known Activations