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

    Neuronpedia

    INDEX
    Explanations

    Furniture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    藝
    -0.07
    consum
    -0.07
     ケ
    -0.06
    ,param
    -0.06
    互
    -0.06
    ')?>
    -0.06
    asl
    -0.06
     reasoned
    -0.06
     جمهوری
    -0.06
    ancellable
    -0.06
    POSITIVE LOGITS
    (forms
    0.07
     hai
    0.07
    mie
    0.07
     Macedonia
    0.06
     Flags
    0.06
     violently
    0.06
     pik
    0.06
     [_
    0.06
    payer
    0.06
     Professor
    0.06
    Act Density 0.041%

    No Known Activations