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

    Neuronpedia

    INDEX
    Explanations

    David

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     viewpoint
    -0.07
     TT
    -0.07
    _ci
    -0.06
    北京
    -0.06
     pls
    -0.06
    download
    -0.06
     viewpoints
    -0.06
    _strings
    -0.06
     smoothing
    -0.06
     revenues
    -0.06
    POSITIVE LOGITS
    ivated
    0.07
     добре
    0.07
     Mass
    0.07
    ичних
    0.06
     False
    0.06
    isan
    0.06
     UNS
    0.06
    ECTOR
    0.06
    scriber
    0.06
     dee
    0.06
    Act Density 0.001%

    No Known Activations