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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    planet
    -0.07
    ________
    -0.07
     diagram
    -0.06
     childhood
    -0.06
     SCALE
    -0.06
     Sahara
    -0.06
    リー
    -0.06
    .mask
    -0.06
    XY
    -0.06
     Raspberry
    -0.06
    POSITIVE LOGITS
    [top
    0.06
    (foo
    0.06
     Plymouth
    0.06
    utas
    0.06
     executing
    0.06
     Osw
    0.06
    landı
    0.06
     tanggal
    0.06
    .readFileSync
    0.06
     angi
    0.06
    Act Density 0.136%

    No Known Activations