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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VEST
    -0.07
     microscope
    -0.07
     PARK
    -0.06
    ARCH
    -0.06
     BRAND
    -0.06
     suff
    -0.06
     danmark
    -0.06
     raid
    -0.06
    ATION
    -0.06
     SHOW
    -0.06
    POSITIVE LOGITS
    As
    0.10
    emies
    0.09
     IDs
    0.08
    Cs
    0.08
     LEDs
    0.08
    s
    0.07
    Bs
    0.07
    Gets
    0.07
    ımı
    0.07
     Bs
    0.07
    Act Density 0.032%

    No Known Activations