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

    Neuronpedia

    INDEX
    Explanations

    Latin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reeves
    -0.07
    versation
    -0.07
     importante
    -0.06
     chỗ
    -0.06
     bele
    -0.06
    inclu
    -0.06
     Mos
    -0.06
     powerless
    -0.06
     ure
    -0.06
    ForResource
    -0.06
    POSITIVE LOGITS
     Latin
    0.08
    atus
    0.07
    ิง
    0.07
    ://%
    0.07
     Dating
    0.06
    思
    0.06
     wheat
    0.06
    annie
    0.06
     antigen
    0.06
    photo
    0.06
    Act Density 0.003%

    No Known Activations