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

    Neuronpedia

    INDEX
    Explanations

    Channel and Pipeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Slots
    0.41
     Deadly
    0.39
     DIR
    0.39
     POLY
    0.38
     lethal
    0.37
     brilliance
    0.36
     deadly
    0.36
     bus
    0.36
     GI
    0.36
     रॉयल
    0.36
    POSITIVE LOGITS
    Group
    0.38
    Enhanced
    0.38
    enhancing
    0.38
    ün
    0.38
    stopPropagation
    0.38
     роз
    0.38
    Cucumber
    0.37
    grouped
    0.37
     группу
    0.37
    ্লা
    0.37
    Act Density 0.000%

    No Known Activations