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

    Neuronpedia

    INDEX
    Explanations

    Gen Z, day grid, initially targeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.46
     M
    0.41
    ,
    0.41
    /
    0.41
     MB
    0.40
    ↵↵
    0.39
     I
    0.39
    How
    0.39
     How
    0.38
    LEE
    0.38
    POSITIVE LOGITS
     sinned
    0.46
    kyverno
    0.45
     criticised
    0.42
     emphasised
    0.42
     celebró
    0.42
     જણાવ્યું
    0.41
    lepší
    0.41
     живе
    0.41
     émissions
    0.41
    echolog
    0.41
    Act Density 0.001%

    No Known Activations