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

    Neuronpedia

    INDEX
    Explanations

    releasing energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کرو
    0.41
     American
    0.38
     Erit
    0.38
     aristocratic
    0.38
    intend
    0.37
     Estonian
    0.37
     Americans
    0.36
     afflict
    0.35
     bestow
    0.35
    颍
    0.35
    POSITIVE LOGITS
    प्ताह
    0.48
     günler
    0.45
    ἃ
    0.42
    ితే
    0.42
    HttpSecurity
    0.40
     কিরূপে
    0.40
     ফেব্রুয়ার
    0.40
     quelli
    0.40
     což
    0.40
     telas
    0.39
    Act Density 0.001%

    No Known Activations