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

    Neuronpedia

    INDEX
    Explanations

    Kund alini

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeta
    0.40
    B
    0.39
    Mob
    0.37
     mob
    0.37
     macron
    0.36
    δ
    0.36
     B
    0.35
    <_
    0.35
    Weil
    0.35
     <
    0.34
    POSITIVE LOGITS
     Vojvod
    0.42
    გილ
    0.41
     Trond
    0.40
    頪
    0.40
    蜓
    0.39
     fills
    0.39
    njih
    0.39
     twenty
    0.38
     crave
    0.38
     unlocks
    0.38
    Act Density 0.000%

    No Known Activations