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

    Neuronpedia

    INDEX
    Explanations

    java classes/types

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REATE
    -0.08
    lar
    -0.08
     larg
    -0.08
    least
    -0.07
    sett
    -0.07
    met
    -0.07
    _det
    -0.07
    extr
    -0.07
    htar
    -0.07
    DIC
    -0.07
    POSITIVE LOGITS
    (rhs
    0.07
    CustomAttributes
    0.06
     Sponge
    0.06
    /sources
    0.06
    温泉
    0.06
    _topics
    0.06
    SequentialGroup
    0.06
    ➸
    0.06
    ဘ
    0.06
    低廉
    0.06
    Act Density 0.005%

    No Known Activations