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

    Neuronpedia

    INDEX
    Explanations

    connecting concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    0.55
    ți
    0.54
    forEach
    0.50
     regelmäßig
    0.48
    ো
    0.48
     einiger
    0.47
    currentTime
    0.47
     dezelfde
    0.47
    érêt
    0.46
    ulière
    0.46
    POSITIVE LOGITS
     an
    0.62
    )
    0.56
    ע
    0.55
     infancy
    0.51
     a
    0.50
    ),
    0.49
     education
    0.47
     can
    0.46
     Institut
    0.46
     where
    0.45
    Act Density 0.040%

    No Known Activations