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

    Neuronpedia

    INDEX
    Explanations

    steve jobs wozniak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sign
    0.39
     Wörter
    0.38
    adro
    0.37
    라인
    0.36
     yolks
    0.35
    Otro
    0.35
    ätzlich
    0.35
    音
    0.35
     आर्यन
    0.34
    দর
    0.34
    POSITIVE LOGITS
     Steve
    1.48
    Steve
    1.38
     steve
    1.10
     स्टी
    0.74
     স্টি
    0.66
     STE
    0.59
     Steven
    0.56
     сте
    0.54
     Clarence
    0.53
    ste
    0.52
    Act Density 0.000%

    No Known Activations