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

    Neuronpedia

    INDEX
    Explanations

    body

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	rd
    -0.07
    ươi
    -0.07
    ak
    -0.06
     StringIO
    -0.06
    uk
    -0.06
    сов
    -0.06
    what
    -0.06
    .jar
    -0.06
    been
    -0.06
    .Listener
    -0.06
    POSITIVE LOGITS
     pall
    0.07
     Perth
    0.06
     samot
    0.06
     اتفاق
    0.06
     BITTE
    0.06
    <bits
    0.06
    .multipart
    0.06
     humiliating
    0.06
    Dropdown
    0.06
     parten
    0.06
    Act Density 0.007%

    No Known Activations