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

    Neuronpedia

    INDEX
    Explanations

    list of items, sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sale
    0.52
    0.45
    Trainer
    0.44
    Transformers
    0.44
    ar
    0.43
    hegan
    0.42
    Captain
    0.42
    물
    0.41
     for
    0.40
    Purchase
    0.40
    POSITIVE LOGITS
     що
    0.48
    دهم
    0.47
    ritu
    0.46
     cirrh
    0.46
    सूचित
    0.46
     sapiens
    0.46
     pensioners
    0.45
     isomer
    0.45
    rieren
    0.45
    нением
    0.45
    Act Density 0.005%

    No Known Activations