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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ขาด
    -0.08
     triển
    -0.07
     obscene
    -0.07
     hostility
    -0.07
     с
    -0.07
     teaching
    -0.07
     소개
    -0.07
     hydrogen
    -0.07
     alongside
    -0.07
     freund
    -0.06
    POSITIVE LOGITS
    enade
    0.08
     chắc
    0.07
    daq
    0.07
    ("&
    0.07
    ascar
    0.06
     invariant
    0.06
    ustral
    0.06
    battery
    0.06
     VARIABLE
    0.06
     OCR
    0.06
    Act Density 0.009%

    No Known Activations