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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     İşte
    -0.08
     Firearms
    -0.07
     diseñ
    -0.07
    殣
    -0.07
    春晚
    -0.07
    ראש
    -0.07
     بتاريخ
    -0.07
     крыш
    -0.07
     kell
    -0.07
     предн
    -0.06
    POSITIVE LOGITS
     blow
    0.08
     minutes
    0.08
    apid
    0.07
    OUTPUT
    0.07
    getMock
    0.07
    🅾
    0.07
     secondary
    0.07
     compound
    0.07
    izia
    0.07
    _customer
    0.07
    Act Density 0.174%

    No Known Activations