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

    Neuronpedia

    INDEX
    Explanations

    personal stories and anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prayer
    -0.08
     addresses
    -0.07
     ise
    -0.07
    ола
    -0.06
     nedenle
    -0.06
     association
    -0.06
    sensor
    -0.06
    ilece
    -0.06
    ustos
    -0.06
     Appeal
    -0.06
    POSITIVE LOGITS
     pang
    0.07
     queryInterface
    0.07
    _activation
    0.06
    �
    0.06
    학년도
    0.06
    .Peek
    0.06
    Рё
    0.06
    inous
    0.06
     ведь
    0.06
    ,},↵
    0.06
    Act Density 0.153%

    No Known Activations