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

    Neuronpedia

    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    comm
    -0.06
    tim
    -0.06
    Equal
    -0.06
     itch
    -0.06
     imports
    -0.06
    His
    -0.06
     mas
    -0.06
    Isl
    -0.06
     rubbed
    -0.06
     Thou
    -0.06
    POSITIVE LOGITS
    峰
    0.07
    หาร
    0.06
    šní
    0.06
    inctions
    0.06
    렇
    0.06
     Charset
    0.06
     Controlled
    0.06
    IRTH
    0.06
    anlı
    0.06
    /rest
    0.06
    Act Density 0.039%

    No Known Activations