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

    Neuronpedia

    INDEX
    Explanations

    is a complicated topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disgusting
    0.50
     abomin
    0.48
     vile
    0.46
    醜
    0.46
     atrocities
    0.46
     merely
    0.46
    仅
    0.46
    仅仅
    0.45
     exacerbate
    0.45
    wtf
    0.45
    POSITIVE LOGITS
     complicated
    0.70
     pretty
    0.59
     really
    0.54
     understandable
    0.50
    complicated
    0.50
     definitely
    0.50
     complicada
    0.49
     multifaceted
    0.47
     compliqué
    0.46
     rooted
    0.45
    Act Density 0.057%

    No Known Activations