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

    Neuronpedia

    INDEX
    Explanations

    right for you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ğ
    0.45
     hiçbir
    0.43
     মানুষ
    0.39
     semoga
    0.39
    responsive
    0.38
    屶
    0.38
     arist
    0.37
     vrij
    0.37
    아야
    0.37
     vast
    0.36
    POSITIVE LOGITS
     Beet
    0.41
    𝗘
    0.39
    idazol
    0.39
     Хотя
    0.38
     muff
    0.37
    edTest
    0.36
    AlignedText
    0.36
    🌦
    0.36
    ControlEvents
    0.36
    なくても
    0.35
    Act Density 0.004%

    No Known Activations