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

    Neuronpedia

    INDEX
    Explanations

    title company insurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atica
    0.43
    മീ
    0.37
    शन
    0.37
     Pisces
    0.36
    entum
    0.36
    INGRE
    0.36
     ПП
    0.36
    季节
    0.36
     AFL
    0.35
    onglet
    0.35
    POSITIVE LOGITS
     company
    0.55
     compañía
    0.47
     companies
    0.45
     launch
    0.45
     कंपनी
    0.45
     examiner
    0.45
    定
    0.45
     empresa
    0.44
    회사
    0.43
     perusahaan
    0.43
    Act Density 0.001%

    No Known Activations