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

    Neuronpedia

    INDEX
    Explanations

    equal and opposite reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कार्यक्रम
    0.43
    कार्यक्रम
    0.42
    0.39
    羥
    0.39
    近日
    0.37
    第一
    0.37
    𒊺
    0.37
    ಬೇಕ
    0.37
    ത്തക
    0.37
    NSMakeRange
    0.36
    POSITIVE LOGITS
     GPIO
    0.35
     ADC
    0.34
     go
    0.33
     GUI
    0.33
     flu
    0.33
     ආ
    0.33
    IF
    0.32
     scale
    0.32
     GPUs
    0.32
    ↵
    0.32
    Act Density 0.004%

    No Known Activations