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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    ruk
    -0.07
    println
    -0.07
    vv
    -0.07
     contrario
    -0.07
    Begin
    -0.07
    StatusLabel
    -0.07
     Gwen
    -0.07
    ۱۶
    -0.07
    Stores
    -0.06
    POSITIVE LOGITS
    ưa
    0.06
    landa
    0.06
     Brazilian
    0.06
    frau
    0.06
    anger
    0.06
    ज
    0.06
    िछ
    0.05
    anness
    0.05
    ибли
    0.05
     Hier
    0.05
    Act Density 0.022%

    No Known Activations