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

    Neuronpedia

    INDEX
    Explanations

    Text fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Domains
    -0.07
     createdBy
    -0.07
     Aad
    -0.07
    аз
    -0.06
    parents
    -0.06
    _deposit
    -0.06
    ertype
    -0.06
     �
    -0.06
    oun
    -0.06
     Tribal
    -0.06
    POSITIVE LOGITS
    viewController
    0.07
     červ
    0.06
    berry
    0.06
     easy
    0.06
    81
    0.06
     também
    0.06
     chuyện
    0.06
     forControlEvents
    0.06
     chắc
    0.06
     호텔
    0.06
    Act Density 0.006%

    No Known Activations