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

    Neuronpedia

    INDEX
    Explanations

    AWS code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     payloads
    -0.07
    383
    -0.07
     sits
    -0.06
     fav
    -0.06
     hailed
    -0.06
    _buy
    -0.06
    770
    -0.06
     від
    -0.06
     bla
    -0.06
     Gameplay
    -0.06
    POSITIVE LOGITS
    プロ
    0.07
     strand
    0.07
     tapes
    0.07
    บาท
    0.07
    uster
    0.07
    γων
    0.07
    ummings
    0.06
    istar
    0.06
    errorMsg
    0.06
    Comput
    0.06
    Act Density 0.005%

    No Known Activations