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

    Neuronpedia

    INDEX
    Explanations

    Confirmations/Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erokee
    -0.07
    (ra
    -0.07
     become
    -0.07
    Louis
    -0.06
    servers
    -0.06
    成為
    -0.06
    .VERSION
    -0.06
     becoming
    -0.06
    whose
    -0.06
     그는
    -0.06
    POSITIVE LOGITS
    tod
    0.07
    reported
    0.06
     investigating
    0.06
     erot
    0.06
    鐘
    0.06
    educ
    0.06
    hari
    0.06
     انتخاب
    0.06
     Sleep
    0.06
     jednotlivých
    0.06
    Act Density 0.026%

    No Known Activations