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

    Neuronpedia

    INDEX
    Explanations

    linear relationship, action verbs, equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matur
    0.50
    covariance
    0.48
     चिह्नित
    0.48
     diritti
    0.48
     soweit
    0.45
     Vielleicht
    0.45
     showrooms
    0.45
     matures
    0.45
    ielleicht
    0.45
    ي
    0.44
    POSITIVE LOGITS
     on
    0.45
    ewnętr
    0.43
    ოველ
    0.43
     compulsive
    0.42
    river
    0.41
     செலு
    0.41
    订阅
    0.40
    ᱕
    0.40
    ʟ
    0.39
    ances
    0.39
    Act Density 0.011%

    No Known Activations