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

    Neuronpedia

    INDEX
    Explanations

    word or phrase completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مگر
    0.41
     හෝ
    0.39
     مضر
    0.39
     purple
    0.38
    又は
    0.38
     Methyl
    0.38
     Purple
    0.37
     Pur
    0.37
     Specify
    0.37
     Peu
    0.37
    POSITIVE LOGITS
    dare
    0.44
    प्लीट
    0.40
    izzano
    0.40
    pidos
    0.40
    ternal
    0.40
    incere
    0.39
    țin
    0.37
    iget
    0.37
    াত্য
    0.37
    ateful
    0.37
    Act Density 0.000%

    No Known Activations