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

    Neuronpedia

    INDEX
    Explanations

    dark, deep, brief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    1.04
    у
    0.89
    োয়া
    0.88
     finns
    0.85
    us
    0.82
    it
    0.81
    লভ
    0.80
    доступ
    0.80
    çe
    0.79
    ні
    0.78
    POSITIVE LOGITS
    τει
    0.84
     Diario
    0.84
    IN
    0.80
    ្ឋ
    0.76
    cji
    0.73
     الدراسي
    0.70
    %%%%%%%%%%%%%%%%
    0.69
    একজন
    0.69
     importance
    0.69
     OI
    0.68
    Act Density 0.001%

    No Known Activations