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

    Neuronpedia

    INDEX
    Explanations

    data and record keeping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aventuras
    0.51
     capitalismo
    0.49
     ആക്രമ
    0.49
     intellectuals
    0.48
     absur
    0.48
     experimentos
    0.48
     monstru
    0.48
    yscrapers
    0.48
     objets
    0.48
     architekt
    0.47
    POSITIVE LOGITS
     records
    0.73
     record
    0.67
    記錄
    0.63
    记录
    0.61
    Records
    0.61
     approval
    0.60
     notification
    0.60
     approving
    0.59
    record
    0.59
    Record
    0.58
    Act Density 0.154%

    No Known Activations