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

    Neuronpedia

    INDEX
    Explanations

    blush, dedicated, plexus, who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.42
     dee
    0.39
     vod
    0.38
     \[
    0.38
     (
    0.37
    open
    0.37
    controls
    0.36
     af
    0.36
    তাম
    0.36
    un
    0.35
    POSITIVE LOGITS
    ถาน
    0.42
    ിലാണ്
    0.40
    ('=
    0.40
    DebuggerNonUser
    0.40
    🉐
    0.39
     obliter
    0.38
     preseason
    0.38
    ⸙
    0.38
    ThemeOverlay
    0.37
     anticoagulant
    0.37
    Act Density 0.001%

    No Known Activations