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

    Neuronpedia

    INDEX
    Explanations

    tea or coffee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dé
    -0.07
     pstmt
    -0.06
     Putin
    -0.06
     STATE
    -0.06
     passer
    -0.06
     güvenlik
    -0.06
     sel
    -0.06
    دار
    -0.06
     FIELD
    -0.06
    으로
    -0.06
    POSITIVE LOGITS
    getMock
    0.07
     человека
    0.07
     생산
    0.06
    едак
    0.06
     Mädchen
    0.06
    就算
    0.06
    die
    0.06
     cavalry
    0.06
     column
    0.06
    \Log
    0.06
    Act Density 0.009%

    No Known Activations