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

    Neuronpedia

    INDEX
    Explanations

    Dana

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    財
    -0.07
     доход
    -0.07
    _PORTS
    -0.07
     AssetImage
    -0.07
    CppObject
    -0.07
    Arthur
    -0.07
    schools
    -0.06
    LAND
    -0.06
    opard
    -0.06
     lunch
    -0.06
    POSITIVE LOGITS
     curs
    0.07
     closed
    0.07
     crates
    0.07
    >>(
    0.07
    ⇡
    0.07
    Proxy
    0.06
    strings
    0.06
    	spec
    0.06
     Fabric
    0.06
    一致好评
    0.06
    Act Density 0.032%

    No Known Activations