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

    Neuronpedia

    INDEX
    Explanations

    failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ottes
    -0.07
     вияви
    -0.07
     dubbed
    -0.07
    ystate
    -0.07
     Zd
    -0.06
    лит
    -0.06
     vỏ
    -0.06
     лес
    -0.06
    $core
    -0.06
     گفت
    -0.06
    POSITIVE LOGITS
     elephants
    0.07
    (serializer
    0.06
     Philips
    0.06
     prepared
    0.06
     high
    0.06
     simple
    0.06
    (groupId
    0.06
     executing
    0.06
     độ
    0.05
    -pointer
    0.05
    Act Density 0.000%

    No Known Activations