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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mandalorian
    0.52
     Alhamdulillah
    0.52
     Zusätzlich
    0.49
     Solidity
    0.48
     Nutzer
    0.47
    闫
    0.46
     Gazprom
    0.46
     Ressourcen
    0.45
     medya
    0.45
     Keci
    0.45
    POSITIVE LOGITS
     Roosevelt
    0.48
     Henry
    0.47
     William
    0.46
    William
    0.45
     J
    0.45
     B
    0.44
     Lincoln
    0.44
    i
    0.44
     George
    0.43
     figures
    0.42
    Act Density 0.009%

    No Known Activations