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

    Neuronpedia

    INDEX
    Explanations

    more on that below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     möchten
    1.05
    ımda
    1.04
    业协会
    1.03
     условии
    1.02
     fiction
    1.02
    などは
    1.01
     revisiting
    1.01
    యిత
    1.00
    blockchain
    0.99
    ibbean
    0.98
    POSITIVE LOGITS
    .
    1.17
    д
    1.14
    n
    1.10
    d
    0.98
     A
    0.98
    un
    0.97
    г
    0.96
    g
    0.95
    ج
    0.92
    h
    0.91
    Act Density 0.085%

    No Known Activations