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

    Neuronpedia

    INDEX
    Explanations

    time and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಬಿ
    0.91
     фаразлары
    0.88
     sucedió
    0.87
    িকাংশ
    0.85
    㑒
    0.85
    旪
    0.83
    SCHEMA
    0.83
     दाता
    0.82
    पालन
    0.82
    ):["
    0.81
    POSITIVE LOGITS
     Day
    0.80
     night
    0.79
     instant
    0.78
     Night
    0.74
     still
    0.70
    0.70
     day
    0.69
     NIGHT
    0.69
     Inst
    0.68
     recognized
    0.68
    Act Density 0.001%

    No Known Activations