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

    Neuronpedia

    INDEX
    Explanations

    sissy transformation and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.47
    zett
    0.47
    ेट्टी
    0.44
    enio
    0.44
    ttier
    0.44
    imiz
    0.44
    вня
    0.44
     textAppearance
    0.44
    ం
    0.43
    swering
    0.43
    POSITIVE LOGITS
     Locomotive
    0.50
     Hulk
    0.44
    </em>
    0.44
     bagels
    0.43
    »)
    0.43
     Rick
    0.42
     Socialism
    0.42
     Lucifer
    0.42
    ↵↵
    0.42
    Councillor
    0.42
    Act Density 0.001%

    No Known Activations