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

    Neuronpedia

    INDEX
    Explanations

    barnacle, Andromeda, Spring, efflorescence, DOM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imamente
    0.54
    adona
    0.54
    يد
    0.52
     Shalom
    0.52
    cey
    0.51
    த
    0.51
    čiu
    0.51
    വിത
    0.50
    kę
    0.50
    startGame
    0.49
    POSITIVE LOGITS
    s
    0.55
     technique
    0.50
    </b>
    0.46
    ের
    0.46
     to
    0.46
     waivers
    0.46
    AI
    0.43
    により
    0.43
     TB
    0.42
    ("-
    0.42
    Act Density 0.000%

    No Known Activations