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

    Neuronpedia

    INDEX
    Explanations

    following fact or let

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realities
    1.01
     dần
    0.94
     irrevers
    0.94
     Governance
    0.94
     بالم
    0.93
     기반
    0.90
     destiny
    0.90
     सालाना
    0.89
    พลัง
    0.89
    VENTION
    0.88
    POSITIVE LOGITS
    ور
    1.02
    tenir
    1.02
     texte
    0.93
    exemple
    0.92
    texte
    0.90
     docteur
    0.90
    icuously
    0.90
    aktadır
    0.90
    careous
    0.89
     intitul
    0.89
    Act Density 2.479%

    No Known Activations