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

    Neuronpedia

    INDEX
    Explanations

    domains and related categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    less
    0.67
    ened
    0.60
    ིས་
    0.54
    rail
    0.53
    num
    0.53
    id
    0.52
    쫒
    0.51
    neath
    0.51
    asus
    0.51
    ener
    0.50
    POSITIVE LOGITS
     industry
    1.24
     enthusiast
    1.13
     enthusiasts
    1.05
     practitioner
    1.04
     terminology
    1.03
    行业的
    1.03
     roundtable
    1.02
     powerhouse
    1.01
    行业
    1.01
     prowess
    0.99
    Act Density 0.401%

    No Known Activations