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

    Neuronpedia

    INDEX
    Explanations

    numer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bras
    -0.07
    خة
    -0.06
    asje
    -0.06
    Act
    -0.06
     burning
    -0.06
    Initially
    -0.06
    běhu
    -0.06
     jacket
    -0.06
     friends
    -0.06
    actly
    -0.06
    POSITIVE LOGITS
     Intern
    0.07
    _simulation
    0.07
     intern
    0.07
    134
    0.07
    ฟ
    0.07
     useEffect
    0.07
    国际
    0.07
     restTemplate
    0.07
     حافظ
    0.06
     비밀
    0.06
    Act Density 0.007%

    No Known Activations