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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Categories
    -0.07
     answering
    -0.06
    リング
    -0.06
    Describe
    -0.06
    _object
    -0.06
     Accessed
    -0.06
    uestion
    -0.06
    _commands
    -0.06
    	session
    -0.06
    (Calendar
    -0.06
    POSITIVE LOGITS
     выдел
    0.07
     متف
    0.07
    PAD
    0.07
     �
    0.07
     chatte
    0.07
     послуг
    0.07
    ekkür
    0.06
     برج
    0.06
     Indi
    0.06
     уча
    0.06
    Act Density 0.020%

    No Known Activations