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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Firewall
    -0.07
    .chunk
    -0.07
    .task
    -0.06
    AdapterFactory
    -0.06
     chuẩn
    -0.06
    tea
    -0.06
    _recent
    -0.06
     AssertionError
    -0.06
    ろう
    -0.06
     Bram
    -0.06
    POSITIVE LOGITS
     efficiencies
    0.07
     useForm
    0.06
     tense
    0.06
     frente
    0.06
     aiding
    0.06
    (attr
    0.06
    olves
    0.06
    attention
    0.06
     تحميل
    0.06
     sửa
    0.06
    Act Density 0.011%

    No Known Activations