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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    argon
    -0.07
     foot
    -0.06
     deposits
    -0.06
    .Deep
    -0.06
     up
    -0.06
    ��
    -0.06
    unami
    -0.06
     حکوم
    -0.06
    ungeon
    -0.06
    hab
    -0.06
    POSITIVE LOGITS
     华
    0.06
     scope
    0.06
    ิวเตอร
    0.06
     가지
    0.06
    <path
    0.06
    之
    0.06
    cestor
    0.06
     सकत
    0.06
    SEND
    0.06
    chunks
    0.06
    Act Density 0.001%

    No Known Activations