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

    Neuronpedia

    INDEX
    Explanations

    colleagues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    四
    -0.08
    定的
    -0.07
     输
    -0.07
    이션
    -0.07
    _Input
    -0.07
    IDTH
    -0.07
     funktion
    -0.06
    .setInput
    -0.06
     tha
    -0.06
    atten
    -0.06
    POSITIVE LOGITS
     colleague
    0.16
     colleagues
    0.16
     coleg
    0.08
     peers
    0.08
     relating
    0.07
    itled
    0.07
     cowork
    0.07
     Col
    0.07
     meslek
    0.07
    `);↵
    0.07
    Act Density 0.005%

    No Known Activations