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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inbox
    -0.06
    atha
    -0.06
     jets
    -0.06
    ру
    -0.06
     person
    -0.06
    了
    -0.06
     trainers
    -0.06
     Tried
    -0.06
     personne
    -0.06
    _upload
    -0.06
    POSITIVE LOGITS
    форма
    0.07
     embarrassment
    0.07
    обрет
    0.06
     stif
    0.06
     spons
    0.06
    overe
    0.06
    Technology
    0.06
    dependency
    0.06
     mohla
    0.06
    (Client
    0.06
    Act Density 0.004%

    No Known Activations