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

    Neuronpedia

    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sembly
    -0.07
    sentence
    -0.06
    seudo
    -0.06
    mlink
    -0.06
     طی
    -0.06
     retrospect
    -0.06
     محمود
    -0.06
     Jennings
    -0.06
     plo
    -0.06
    okit
    -0.06
    POSITIVE LOGITS
     Mour
    0.07
    >{↵
    0.07
    ภายใน
    0.07
    "</
    0.07
    women
    0.07
    0.06
     Ltd
    0.06
     women
    0.06
     �
    0.06
    '},↵
    0.06
    Act Density 0.032%

    No Known Activations