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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ceremonies
    -0.07
    rape
    -0.07
     Playground
    -0.07
    _CTRL
    -0.06
     registro
    -0.06
    :nil
    -0.06
     soc
    -0.06
    配
    -0.06
    -corner
    -0.06
     creado
    -0.06
    POSITIVE LOGITS
    ặn
    0.07
     «
    0.07
    онів
    0.07
     کار
    0.07
    Recogn
    0.07
    ных
    0.06
    ửi
    0.06
    Fold
    0.06
     Ther
    0.06
     talent
    0.06
    Act Density 0.000%

    No Known Activations