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

    Neuronpedia

    INDEX
    Explanations

    instructions and reminders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &a
    -0.08
     ｰ
    -0.07
    ^\
    -0.06
    �
    -0.06
    ца
    -0.06
    -before
    -0.06
    >}'
    -0.06
    宽
    -0.06
    /dc
    -0.06
     Evrop
    -0.06
    POSITIVE LOGITS
    Carrier
    0.07
    فع
    0.06
    igious
    0.06
     Yamaha
    0.06
     vera
    0.06
    콘
    0.06
     Everton
    0.06
    avings
    0.06
    سلام
    0.06
     jednání
    0.06
    Act Density 0.090%

    No Known Activations