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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     civilians
    -0.07
    oodoo
    -0.06
    aturday
    -0.06
    (targets
    -0.06
    .Bold
    -0.06
    jylland
    -0.06
    AUTHORIZED
    -0.06
    ㆍ동
    -0.06
    ,d
    -0.06
     hijos
    -0.06
    POSITIVE LOGITS
    Tabs
    0.07
    ns
    0.06
    λμ
    0.06
     Κό
    0.06
    Ti
    0.06
     Applies
    0.06
     Joined
    0.06
     ξ
    0.06
    .Abs
    0.06
    elerin
    0.06
    Act Density 0.033%

    No Known Activations