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

    Neuronpedia

    INDEX
    Explanations

    consequential damages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kon
    0.45
     Conrad
    0.43
     Conor
    0.43
     Conley
    0.40
     Con
    0.40
     conformations
    0.39
     CON
    0.38
    ZC
    0.38
     Conspiracy
    0.38
     kon
    0.38
    POSITIVE LOGITS
    idental
    0.47
     kira
    0.40
    <<"
    0.40
    пример
    0.38
    kir
    0.38
    ⠀⠀⠀⠀
    0.38
    .$;
    0.37
     piano
    0.36
    кер
    0.36
    example
    0.35
    Act Density 0.000%

    No Known Activations