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

    Neuronpedia

    INDEX
    Explanations

    stddef

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vlan
    -0.07
     typing
    -0.07
    放送
    -0.07
    apters
    -0.07
    mono
    -0.06
     yayın
    -0.06
     thêm
    -0.06
     mutable
    -0.06
    über
    -0.06
    Specifies
    -0.06
    POSITIVE LOGITS
     Eck
    0.07
     attendees
    0.06
    ากล
    0.06
    .AspNet
    0.06
     الز
    0.06
    _dirs
    0.06
     dismiss
    0.06
    �
    0.06
    실
    0.06
    	array
    0.06
    Act Density 0.001%

    No Known Activations