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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pues
    -0.07
    "f
    -0.07
     сфері
    -0.07
     ');
↵
    -0.07
     pencil
    -0.06
    _da
    -0.06
    강
    -0.06
    ihu
    -0.06
    Spin
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     they
    0.07
    监
    0.06
    ysics
    0.06
    .blit
    0.06
    (ai
    0.06
     their
    0.06
    사의
    0.06
     امنیت
    0.06
     simplement
    0.06
    _Parse
    0.06
    Act Density 0.054%

    No Known Activations