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

    Neuronpedia

    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ($"
    -0.07
    .services
    -0.07
    splash
    -0.07
     POR
    -0.07
    .intro
    -0.06
    ibNameOrNil
    -0.06
     "@"
    -0.06
    .zh
    -0.06
    HEL
    -0.06
     Buffy
    -0.06
    POSITIVE LOGITS
     around
    0.13
     Around
    0.10
    Around
    0.09
    around
    0.08
    っく
    0.07
     autour
    0.07
     biri
    0.07
     tame
    0.07
     kolem
    0.07
    pherical
    0.07
    Act Density 0.020%

    No Known Activations