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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scenes
    -0.07
     Fl
    -0.07
     responsible
    -0.07
    马
    -0.07
    -common
    -0.07
     deputies
    -0.07
     placements
    -0.07
    bcc
    -0.07
    ави
    -0.07
    DTD
    -0.06
    POSITIVE LOGITS
     eig
    0.06
     Except
    0.06
    willReturn
    0.06
    №№
    0.06
    statusCode
    0.06
     Гар
    0.06
    �
    0.05
    imagen
    0.05
     Thu
    0.05
    (Const
    0.05
    Act Density 0.017%

    No Known Activations