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

    Neuronpedia

    INDEX
    Explanations

    first prompt, of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Apothe
    0.47
     Strategic
    0.45
     Disabilities
    0.44
     Psychology
    0.44
     withdrawal
    0.44
    )(((
    0.43
     Digestive
    0.43
     보니
    0.43
     Hilde
    0.43
     Remedy
    0.42
    POSITIVE LOGITS
     Неза
    0.44
    чают
    0.44
    Я
    0.43
    荖
    0.43
    engineered
    0.43
    istemas
    0.43
     உல
    0.43
     geeign
    0.42
    ajuan
    0.42
    ived
    0.42
    Act Density 0.000%

    No Known Activations