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

    Neuronpedia

    INDEX
    Explanations

    workload and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ண்ட
    0.44
    Signal
    0.42
    ள
    0.42
    viamente
    0.41
    logic
    0.41
    ောင်
    0.40
    lení
    0.40
    performance
    0.40
     معمولی
    0.39
    izing
    0.39
    POSITIVE LOGITS
     dogs
    0.52
     Iran
    0.49
     enzyme
    0.47
    Η
    0.47
     matriline
    0.46
     lua
    0.46
     tetr
    0.46
     Greece
    0.45
     мо
    0.44
     Virginia
    0.44
    Act Density 0.000%

    No Known Activations