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

    Neuronpedia

    INDEX
    Explanations

    language model research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lesions
    0.44
     instruments
    0.41
     reptiles
    0.40
     preserve
    0.39
     materially
    0.39
     denominators
    0.39
     কৌশল
    0.38
    Instruments
    0.38
     stimuli
    0.38
     preclude
    0.38
    POSITIVE LOGITS
    dateTimePicker
    0.39
    ۪
    0.38
    esy
    0.37
     Яндекс
    0.36
    钻
    0.35
    ណ្ត
    0.35
    Cer
    0.35
    aad
    0.34
    钡
    0.34
     باز
    0.34
    Act Density 0.000%

    No Known Activations