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

    Neuronpedia

    INDEX
    Explanations

    React useState declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.86
     lungo
    1.85
    yak
    1.80
    seca
    1.80
    yog
    1.74
    yce
    1.70
    pizza
    1.69
    ভেদ
    1.65
    girlfriend
    1.65
    Bankruptcy
    1.60
    POSITIVE LOGITS
    円以上
    1.42
    꼐
    1.42
     अजि
    1.41
    怎麼
    1.40
    ‖</
    1.38
     совсем
    1.37
    புது
    1.36
     itibaren
    1.35
    کے
    1.32
    รูป
    1.32
    Act Density 0.008%

    No Known Activations