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

    Neuronpedia

    INDEX
    Explanations

    Good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ですが
    -0.09
     certaines
    -0.09
    ，但是
    -0.09
    waarde
    -0.09
     Certaines
    -0.08
    REMOTE
    -0.08
     ressemble
    -0.08
     όμως
    -0.08
     Beob
    -0.08
     aquellas
    -0.08
    POSITIVE LOGITS
     confirms
    0.13
    验证
    0.12
    確認
    0.12
    确认
    0.11
     confirmed
    0.11
     സ്ഥിരീകര
    0.11
     correctness
    0.11
     confirming
    0.11
    驗
    0.10
     confirmé
    0.10
    Act Density 0.049%

    No Known Activations