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

    Neuronpedia

    INDEX
    Explanations

    concepts in diverse fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SUVs
    0.50
     versions
    0.50
     GPUs
    0.49
     Nazis
    0.49
    ные
    0.49
     mga
    0.49
     iPads
    0.46
     croissants
    0.46
     CDs
    0.46
    antoms
    0.45
    POSITIVE LOGITS
    和一个
    0.70
     любого
    0.60
     veya
    0.56
     რომელიც
    0.56
     एखा
    0.55
    或其他
    0.55
    ेलर
    0.55
    යක්
    0.54
    就是一个
    0.54
     ወይም
    0.54
    Act Density 0.577%

    No Known Activations