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

    Neuronpedia

    INDEX
    Explanations

    end of code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CONTACT
    0.40
    LETE
    0.39
     piet
    0.39
     Supervision
    0.38
     مخاط
    0.37
     chutney
    0.37
     numerador
    0.37
     Armani
    0.37
    神奇
    0.36
     jau
    0.36
    POSITIVE LOGITS
     оконча
    0.54
    finish
    0.51
     final
    0.50
    最後に
    0.49
     završ
    0.48
    Finish
    0.48
     schließlich
    0.47
     sonunda
    0.46
    最終
    0.46
     завер
    0.46
    Act Density 0.322%

    No Known Activations