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

    Neuronpedia

    INDEX
    Explanations

    engine specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    terr
    -0.07
    	st
    -0.07
    арч
    -0.06
    -dot
    -0.06
    .vocab
    -0.06
    /b
    -0.06
    )reader
    -0.06
    �
    -0.06
    tvrt
    -0.06
     cmb
    -0.06
    POSITIVE LOGITS
    dag
    0.07
     SMTP
    0.07
    637
    0.07
     Mã
    0.06
     long
    0.06
    _friends
    0.06
     high
    0.06
    mít
    0.06
     Kế
    0.06
    AsStringAsync
    0.06
    Act Density 0.001%

    No Known Activations