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

    Neuronpedia

    INDEX
    Explanations

    slides and presentation materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     confi
    0.48
     discriminated
    0.48
     redução
    0.47
     alleviated
    0.45
     satisfied
    0.44
     redu
    0.43
     reducible
    0.43
     inputted
    0.43
     encountered
    0.42
     clarification
    0.42
    POSITIVE LOGITS
    Party
    0.46
    Sweep
    0.43
    Conclusions
    0.42
     የወ
    0.42
     or
    0.41
    Skills
    0.41
    Che
    0.40
     rester
    0.40
    Crane
    0.39
    کر
    0.38
    Act Density 0.002%

    No Known Activations