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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    审
    -0.07
     archivos
    -0.07
     cloth
    -0.07
     dogs
    -0.07
    _encoder
    -0.07
     reviews
    -0.06
    -(
    -0.06
     strings
    -0.06
    _word
    -0.06
    世紀
    -0.06
    POSITIVE LOGITS
    ;?#
    0.06
     mostr
    0.06
    bee
    0.06
     욕
    0.06
     bài
    0.06
     daher
    0.06
     Verde
    0.06
     đãi
    0.06
    なた
    0.06
    ุงเทพ
    0.06
    Act Density 0.061%

    No Known Activations