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

    Neuronpedia

    INDEX
    Explanations

    shifts and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VITY
    0.52
    ATORS
    0.49
     punishable
    0.48
     dateFormatter
    0.44
     топлива
    0.44
    HBO
    0.43
    Executed
    0.43
    кновен
    0.43
     polygonal
    0.42
    CBUUID
    0.42
    POSITIVE LOGITS
     conect
    0.41
     norm
    0.41
     repellat
    0.40
     are
    0.40
     hank
    0.38
    がなく
    0.38
     col
    0.38
    ،
    0.38
     emoción
    0.38
    龰
    0.37
    Act Density 0.008%

    No Known Activations