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

    Neuronpedia

    INDEX
    Explanations

    world wars and 4th of july

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.54
    均匀
    0.53
    𝑧
    0.50
    ﺰ
    0.50
     lazım
    0.49
     često
    0.49
    4
    0.48
    点
    0.48
     хотите
    0.48
    ↵
    0.48
    POSITIVE LOGITS
    Í
    0.48
     hostages
    0.48
     presiden
    0.47
     artikel
    0.45
    ᒥ
    0.45
     Presiden
    0.44
     was
    0.43
     iunie
    0.43
    }
    0.43
     soldados
    0.42
    Act Density 0.105%

    No Known Activations