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

    Neuronpedia

    INDEX
    Explanations

    past hour, his, maintenance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exasper
    0.46
     ent
    0.45
     ens
    0.45
     ensues
    0.44
     dez
    0.44
     vend
    0.44
     api
    0.44
     rejo
    0.44
     bio
    0.43
     particular
    0.43
    POSITIVE LOGITS
    mless
    0.46
    v
    0.44
    termine
    0.44
    viable
    0.43
    doesn
    0.43
    brough
    0.42
     Attitudes
    0.42
    oxides
    0.42
    b
    0.42
    ascus
    0.41
    Act Density 0.001%

    No Known Activations