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

    Neuronpedia

    INDEX
    Explanations

    rod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CID
    -0.06
    대의
    -0.06
    sko
    -0.06
     fds
    -0.06
    _client
    -0.06
    dojo
    -0.06
     abortion
    -0.06
    �
    -0.06
     hüc
    -0.06
    xBA
    -0.06
    POSITIVE LOGITS
     perpetrator
    0.07
     exploitation
    0.06
    visible
    0.06
     Trainer
    0.06
     Stephanie
    0.06
     Invisible
    0.06
     Disabled
    0.06
    ">--}}↵
    0.06
     Communities
    0.06
     Shipping
    0.06
    Act Density 0.019%

    No Known Activations