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

    Neuronpedia

    INDEX
    Explanations

    Trigger words/phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diseñador
    -0.07
     nhân
    -0.07
     nationality
    -0.07
    &display
    -0.06
    โปร
    -0.06
    �
    -0.06
     Vacuum
    -0.06
     mins
    -0.06
     Needless
    -0.06
     synonyms
    -0.06
    POSITIVE LOGITS
    ifs
    0.06
     Boulevard
    0.06
    (od
    0.06
    (issue
    0.06
     Ι
    0.06
    needed
    0.06
    hk
    0.06
    cms
    0.06
     restraint
    0.06
    EDI
    0.06
    Act Density 0.014%

    No Known Activations