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

    Neuronpedia

    INDEX
    Explanations

    It was a control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.40
    ა
    1.30
     trump
    1.22
     critical
    1.20
    м
    1.19
     cheek
    1.18
    かしい
    1.17
    are
    1.15
    م
    1.14
     cookie
    1.13
    POSITIVE LOGITS
    儡
    1.30
    delà
    1.11
     situazione
    1.10
     rağmen
    1.08
    犷
    1.07
    >∈</
    1.07
     Accenture
    1.07
     beraber
    1.06
     aşağıdaki
    1.06
    EXAMPLE
    1.05
    Act Density 0.000%

    No Known Activations