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

    Neuronpedia

    INDEX
    Explanations

    safety and training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Withdraw
    -0.07
    Withdraw
    -0.07
    Republic
    -0.07
     Peer
    -0.07
    Hospital
    -0.06
     Για
    -0.06
    Base
    -0.06
    Brad
    -0.06
    іли
    -0.06
    이라는
    -0.06
    POSITIVE LOGITS
    [axis
    0.06
    aviour
    0.06
    appable
    0.06
     م
    0.06
    acht
    0.06
    urple
    0.06
     cứu
    0.06
    etric
    0.06
     tail
    0.06
    =result
    0.06
    Act Density 0.029%

    No Known Activations