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

    Neuronpedia

    INDEX
    Explanations

    academic papers and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gamepad
    0.46
    steuerung
    0.46
     waveform
    0.46
     ナチュラル
    0.45
     スマート
    0.45
     ハート
    0.44
    semaphore
    0.44
     coronavirus
    0.43
     motherboard
    0.43
    éf
    0.43
    POSITIVE LOGITS
     academic
    0.99
     scholarly
    0.93
     Academic
    0.91
    学术
    0.89
    科研
    0.88
    academic
    0.88
     postdoctoral
    0.86
    Academic
    0.86
     akademik
    0.84
     académico
    0.83
    Act Density 0.109%

    No Known Activations