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

    Neuronpedia

    INDEX
    Explanations

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     before
    -0.08
     час
    -0.07
     refusing
    -0.06
     nothing
    -0.06
     �
    -0.06
    modelo
    -0.06
     intending
    -0.06
     ἀ
    -0.06
    ////////////////////////////////////////////////////////////////////////
    -0.06
     missionary
    -0.06
    POSITIVE LOGITS
    ={}
    0.06
    yme
    0.06
     взаєм
    0.06
    %;">↵
    0.06
    181
    0.06
    .goto
    0.06
    灰
    0.06
     �
    0.06
    _Red
    0.06
           ↵↵
    0.06
    Act Density 0.000%

    No Known Activations