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

    Neuronpedia

    INDEX
    Explanations

    error for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಎರಡ
    0.37
     presenceData
    0.36
    शिलाजीत
    0.36
     gala
    0.36
     DataSet
    0.34
     girder
    0.34
     гара
    0.33
     கார்ப
    0.33
    loggedin
    0.33
     DataSource
    0.33
    POSITIVE LOGITS
     Attribute
    0.38
    Action
    0.38
     Operations
    0.38
     Action
    0.36
    attribute
    0.36
     Controls
    0.34
     MOB
    0.34
     اقدام
    0.34
    Attribute
    0.34
     unusable
    0.34
    Act Density 0.002%

    No Known Activations