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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相关
    -0.06
    Least
    -0.06
     systému
    -0.06
    Decode
    -0.06
     ilişkin
    -0.06
    Block
    -0.06
    :::::
    -0.05
     underwater
    -0.05
    \Lib
    -0.05
    SHIFT
    -0.05
    POSITIVE LOGITS
    .ImageField
    0.07
     '':↵
    0.07
     itching
    0.07
     compositions
    0.06
     Москва
    0.06
     Poly
    0.06
    avail
    0.06
     extent
    0.06
    _CHANGE
    0.06
    ционный
    0.06
    Act Density 0.059%

    No Known Activations