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

    Neuronpedia

    INDEX
    Explanations

    following a trail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    feu
    0.47
     зазна
    0.46
    weg
    0.46
    threads
    0.46
    phen
    0.45
    pyrazin
    0.43
    ling
    0.43
    round
    0.43
    tez
    0.43
    voja
    0.43
    POSITIVE LOGITS
     electron
    0.59
     incentive
    0.56
     intestine
    0.51
     microscope
    0.48
     grape
    0.48
     incentives
    0.47
     desk
    0.47
     mirror
    0.47
     laurels
    0.47
     tobacco
    0.46
    Act Density 0.000%

    No Known Activations