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

    Neuronpedia

    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    THAT
    0.44
    だったら
    0.40
    кування
    0.38
    此同时
    0.38
     cogeneration
    0.37
    NOW
    0.36
    βο
    0.35
    زش
    0.35
    ്യാപ
    0.35
     partenariat
    0.35
    POSITIVE LOGITS
    ↵↵↵↵
    0.62
     Here
    0.62
     😊
    0.61
    ↵↵↵
    0.61
    ↵↵↵↵↵↵
    0.59
     Firstly
    0.57
     Below
    0.55
    ↵↵↵↵↵
    0.54
    <h3>
    0.54
     Choose
    0.54
    Act Density 0.000%

    No Known Activations