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

    Neuronpedia

    INDEX
    Explanations

    drug use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utz
    -0.07
     marriages
    -0.07
    """
    -0.07
    Mur
    -0.07
     Face
    -0.07
    .rotate
    -0.07
     Joyce
    -0.07
     баб
    -0.07
     Levy
    -0.07
     tower
    -0.07
    POSITIVE LOGITS
    ैट
    0.06
    Existing
    0.06
     가진
    0.06
    –
    0.06
    IFS
    0.06
    IFn
    0.06
     электрон
    0.06
     Türkiye
    0.06
    .getSimpleName
    0.06
    ｝
    0.06
    Act Density 0.017%

    No Known Activations