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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Haus
    -0.07
     Kirst
    -0.07
    屋子
    -0.07
    "nil
    -0.07
     Pearce
    -0.07
    Opcode
    -0.07
    Ĵ
    -0.07
     Cornel
    -0.07
    띕
    -0.07
     marital
    -0.06
    POSITIVE LOGITS
    低估
    0.07
    >`
    0.06
     apro
    0.06
    BR
    0.06
     applaud
    0.06
    (PRO
    0.06
    ',{'
    0.06
    (){↵
    0.06
    徙
    0.06
     mamm
    0.06
    Act Density 0.006%

    No Known Activations