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

    Neuronpedia

    INDEX
    Explanations

    legends live on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tikz
    0.42
     uneasy
    0.40
    荠
    0.40
    κρι
    0.40
    Hazard
    0.39
    ertown
    0.38
    utas
    0.37
     nutri
    0.36
     peacefully
    0.36
     probs
    0.36
    POSITIVE LOGITS
    mam
    0.40
    gg
    0.39
    sib
    0.39
     GG
    0.39
     sibling
    0.39
    conventional
    0.38
     eingel
    0.38
    ன்கள்
    0.38
     IRC
    0.38
    ducting
    0.38
    Act Density 0.000%

    No Known Activations