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

    Neuronpedia

    INDEX
    Explanations

    your message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    荣誉
    0.71
    ରି
    0.71
     emeritus
    0.66
     faktor
    0.66
     wład
    0.65
     permeability
    0.64
    rmse
    0.62
    addPreferred
    0.62
     повышение
    0.61
    děpodob
    0.60
    POSITIVE LOGITS
     content
    1.46
     tasks
    1.40
     contents
    1.35
    内容
    1.33
     messages
    1.32
     contenido
    1.26
    コンテンツ
    1.25
     projects
    1.24
     contenuti
    1.24
     items
    1.23
    Act Density 4.705%

    No Known Activations