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

    Neuronpedia

    INDEX
    Explanations

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ʜ
    0.55
    ᴛ
    0.50
    ɢ
    0.50
    Fade
    0.47
    нува
    0.47
    SizePolicy
    0.46
    Ո
    0.46
    ことになる
    0.46
    Bin
    0.45
    מס
    0.45
    POSITIVE LOGITS
    er
    0.52
    and
    0.52
    ানুভূতি
    0.47
    اً
    0.45
     summary
    0.44
    it
    0.43
    वृत्ति
    0.43
     mesti
    0.42
    z
    0.41
     not
    0.40
    Act Density 0.055%

    No Known Activations