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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scientology
    -0.07
     electrodes
    -0.07
     pictures
    -0.07
    fu
    -0.07
     loi
    -0.06
    ertificate
    -0.06
    Def
    -0.06
    クロ
    -0.06
     SYN
    -0.06
    umsuz
    -0.06
    POSITIVE LOGITS
    íc
    0.08
     полос
    0.06
     distributes
    0.06
    などの
    0.06
     thankful
    0.06
    sono
    0.06
     έχ
    0.06
    ิว
    0.06
     буд
    0.06
    _eq
    0.06
    Act Density 0.011%

    No Known Activations