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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    designation
    -0.08
     Nikki
    -0.07
     please
    -0.07
     congressman
    -0.07
    (station
    -0.07
    命中
    -0.06
    曹操
    -0.06
     chefs
    -0.06
    院士
    -0.06
     gene
    -0.06
    POSITIVE LOGITS
    utos
    0.07
    �
    0.07
    �
    0.07
    -sector
    0.07
     perpetual
    0.07
    CDATA
    0.07
    &oacute
    0.07
    uml
    0.07
    UDO
    0.07
     dotyc
    0.07
    Act Density 0.002%

    No Known Activations