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

    Neuronpedia

    INDEX
    Explanations

    IA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.57
     a
    0.49
    1
    0.43
    DIRS
    0.43
     finger
    0.43
     Finger
    0.42
     prophets
    0.41
    ut
    0.41
     waters
    0.40
    ORM
    0.40
    POSITIVE LOGITS
     মো
    0.49
    eş
    0.48
    лося
    0.47
    эл
    0.47
    ケート
    0.46
     $)
    0.45
    ்சை
    0.45
    ेट
    0.45
    $&
    0.45
     mają
    0.45
    Act Density 0.007%

    No Known Activations