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

    Neuronpedia

    INDEX
    Explanations

    numbered lists item two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ispit
    0.40
    jdt
    0.38
     postings
    0.37
     carcinogenic
    0.37
     fue
    0.36
    asile
    0.36
    linic
    0.36
    embangan
    0.35
     IEC
    0.35
    გენ
    0.35
    POSITIVE LOGITS
    以上に
    0.39
    Replacing
    0.38
    篁
    0.37
    ächst
    0.37
    Took
    0.36
    Fond
    0.36
     faudra
    0.35
    Rack
    0.35
    Personally
    0.34
     نظام
    0.34
    Act Density 0.002%

    No Known Activations