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

    Neuronpedia

    INDEX
    Explanations

    other or similarly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fences
    0.27
    ╽
    0.26
     sich
    0.26
     então
    0.26
     کردن
    0.26
     spirito
    0.26
    ائل
    0.26
     soient
    0.26
     się
    0.25
     sedent
    0.25
    POSITIVE LOGITS
     другими
    0.35
     similarly
    0.34
     інші
    0.32
     других
    0.31
     другие
    0.30
    Similarly
    0.30
    other
    0.30
     other
    0.30
    另一种
    0.29
     Similarly
    0.29
    Act Density 0.284%

    No Known Activations