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

    Neuronpedia

    INDEX
    Explanations

    Newfoundland

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aliqu
    0.30
     இதில்
    0.28
     behöver
    0.28
     🔥
    0.27
    在這個
    0.27
    ంచెం
    0.27
     beasts
    0.26
    𝑑
    0.26
    🫡
    0.26
    🫣
    0.26
    POSITIVE LOGITS
     ursprünglich
    0.33
     fundador
    0.32
    originally
    0.29
     Originally
    0.29
     founder
    0.29
     Newfoundland
    0.28
    Originally
    0.28
     Fundación
    0.28
     fundraising
    0.28
     brainchild
    0.28
    Act Density 0.083%

    No Known Activations