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

    Neuronpedia

    INDEX
    Explanations

    public use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     रिपोर्ट्स
    0.71
     হৃদ
    0.68
    原則
    0.68
    Technical
    0.67
     switching
    0.65
     defaults
    0.65
    并将
    0.65
     Switching
    0.64
    commits
    0.63
    这件事
    0.63
    POSITIVE LOGITS
     use
    1.94
    use
    1.63
     Use
    1.55
    Use
    1.53
     uso
    1.43
     consumption
    1.39
     consideration
    1.34
     bruk
    1.27
     consumo
    1.26
     gebruik
    1.26
    Act Density 0.134%

    No Known Activations