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

    Neuronpedia

    INDEX
    Explanations

    key: value pairs like "value": "04/24"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    माइंडर
    0.37
    Ს
    0.34
    Პ
    0.33
    atthaya
    0.33
    মিনা
    0.33
    खास्त
    0.32
    ጠት
    0.32
    ?”.
    0.32
    worldly
    0.31
    AttributeInfo
    0.31
    POSITIVE LOGITS
    0.41
     similarly
    0.37
    '
    0.34
        
    0.34
     etc
    0.33
       
    0.33
    同様
    0.32
     Similarly
    0.31
     November
    0.31
     E
    0.31
    Act Density 0.063%

    No Known Activations