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

    Neuronpedia

    INDEX
    Explanations

    parenthetical clarifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fel
    0.44
    subunit
    0.42
     वन
    0.42
     Nuggets
    0.40
     Filip
    0.40
    ь
    0.40
    वर्क
    0.39
    컨
    0.39
    Jeg
    0.39
     deny
    0.39
    POSITIVE LOGITS
     oran
    0.44
     enrolled
    0.43
     enroll
    0.42
    ന്നാ
    0.42
    erce
    0.41
    select
    0.41
    register
    0.41
    flux
    0.41
    readLine
    0.40
    turtle
    0.40
    Act Density 0.004%

    No Known Activations