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

    Neuronpedia

    INDEX
    Explanations

    police reports/testimony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <span
    -0.07
    421
    -0.06
    사가
    -0.06
    ちょっと
    -0.06
     courageous
    -0.06
     difícil
    -0.06
     rich
    -0.06
     Mary
    -0.06
     forgotten
    -0.06
     Vanderbilt
    -0.06
    POSITIVE LOGITS
     tutoring
    0.06
    onnement
    0.06
     rnn
    0.06
    pies
    0.06
    \Helpers
    0.06
    ;o
    0.06
     erro
    0.06
    -original
    0.06
    periment
    0.06
     nặng
    0.06
    Act Density 0.034%

    No Known Activations