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

    Neuronpedia

    INDEX
    Explanations

    leading to uncertainty or risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.46
    砚
    0.45
     elucidated
    0.43
    ()},
    0.42
    ),
    0.42
    িন্ন
    0.40
    माण
    0.39
    тах
    0.39
    illae
    0.39
    },
    0.38
    POSITIVE LOGITS
     takeover
    0.47
    u
    0.47
     loudest
    0.46
     sprinting
    0.45
     בל
    0.45
     tini
    0.45
     fastest
    0.45
     Ingers
    0.44
     הח
    0.44
     Serena
    0.44
    Act Density 0.001%

    No Known Activations