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

    Neuronpedia

    INDEX
    Explanations

    ]( Me giving instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stand
    0.37
     sprem
    0.34
     méth
    0.34
     verb
    0.33
     oleh
    0.33
     chemistry
    0.33
     bibli
    0.32
     caud
    0.32
     le
    0.32
     steht
    0.31
    POSITIVE LOGITS
    wholesale
    0.54
    cheap
    0.48
    seo
    0.47
    https
    0.46
    Cheap
    0.45
     Cryptocurrency
    0.44
    bitcoin
    0.43
    buy
    0.43
    激安
    0.43
    Https
    0.43
    Act Density 0.004%

    No Known Activations