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

    Neuronpedia

    INDEX
    Explanations

    ! followed by 😊

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     également
    0.39
     also
    0.38
     somewhat
    0.38
     jacket
    0.38
     također
    0.38
     সাধারণভাবে
    0.38
     rune
    0.38
     optionally
    0.38
     include
    0.37
     turntable
    0.37
    POSITIVE LOGITS
     niemand
    0.48
    Nunca
    0.48
    Nobody
    0.44
    Isn
    0.44
    決して
    0.43
     Nobody
    0.42
     complacency
    0.42
     sufrimiento
    0.42
     orgullo
    0.41
     nadie
    0.41
    Act Density 3.027%

    No Known Activations