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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coords
    -0.07
    bad
    -0.07
    >')↵
    -0.07
    powiedzieć
    -0.07
    .ImageView
    -0.07
    multipart
    -0.07
    _published
    -0.07
     publishers
    -0.07
    Identifier
    -0.07
     definitions
    -0.06
    POSITIVE LOGITS
    零碎
    0.07
     jenter
    0.07
     мень
    0.07
    改
    0.07
     resolving
    0.07
     conta
    0.06
    暢
    0.06
    藝
    0.06
    atics
    0.06
    订
    0.06
    Act Density 0.173%

    No Known Activations