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

    Neuronpedia

    INDEX
    Explanations

    bug tracking and bounty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    额外
    0.43
     Chaney
    0.42
     wealthiest
    0.39
     Distillery
    0.39
     decis
    0.38
    utional
    0.38
     appris
    0.38
     kontinu
    0.38
    แหน่ง
    0.38
    棦
    0.38
    POSITIVE LOGITS
    zilla
    0.52
    zip
    0.42
    Guide
    0.39
    bati
    0.38
     WD
    0.37
    Lord
    0.37
     thing
    0.36
    col
    0.36
    eng
    0.35
    caller
    0.35
    Act Density 0.000%

    No Known Activations