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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disrupted
    -0.07
     Warn
    -0.07
    icter
    -0.07
    Torrent
    -0.06
     loadChildren
    -0.06
     hus
    -0.06
     Hassan
    -0.06
    (issue
    -0.06
    �
    -0.06
    !),
    -0.06
    POSITIVE LOGITS
    _=
    0.07
    ывая
    0.07
     уровня
    0.06
    ']↵↵↵
    0.06
    .Http
    0.06
     overlay
    0.06
    最佳
    0.06
    etect
    0.06
     cryptography
    0.06
    tle
    0.06
    Act Density 0.050%

    No Known Activations