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

    Neuronpedia

    INDEX
    Explanations

    science fiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ritten
    -0.06
    .chrome
    -0.06
     يق
    -0.06
     abortion
    -0.06
    �u
    -0.06
     Picture
    -0.06
    瞬
    -0.06
    RULE
    -0.06
     StatefulWidget
    -0.06
    osaic
    -0.06
    POSITIVE LOGITS
    ，如
    0.07
     нія
    0.07
     tempted
    0.06
    Tuy
    0.06
     hell
    0.06
    656
    0.06
    972
    0.06
    ″
    0.06
    -names
    0.06
    .ALIGN
    0.06
    Act Density 0.015%

    No Known Activations