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

    Neuronpedia

    INDEX
    Explanations

    cannabis, cannibal, Kannada

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    excluding
    0.40
     afloat
    0.40
     excluding
    0.39
    뢨
    0.39
    বৃন্দ
    0.39
     successors
    0.38
    烨
    0.38
    തിൽ
    0.37
    *_
    0.37
     userdata
    0.37
    POSITIVE LOGITS
     cannab
    0.50
     Cann
    0.50
     cann
    0.49
     cannibal
    0.49
    cann
    0.47
    Cann
    0.47
    abis
    0.46
    Kann
    0.44
     bist
    0.42
     kann
    0.40
    Act Density 0.002%

    No Known Activations