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

    Neuronpedia

    INDEX
    Explanations

    looking things up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pecified
    -0.06
     Agility
    -0.06
    amide
    -0.06
     Chen
    -0.06
     completes
    -0.06
     marg
    -0.06
     campos
    -0.06
    ツ
    -0.05
    塞
    -0.05
     ー
    -0.05
    POSITIVE LOGITS
    bellion
    0.07
    (...)↵
    0.07
     телеф
    0.07
    sei
    0.07
     travelers
    0.07
    _Order
    0.06
     Alumni
    0.06
     Spells
    0.06
    Verify
    0.06
    ansion
    0.06
    Act Density 0.104%

    No Known Activations