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

    Neuronpedia

    INDEX
    Explanations

    aiming for neutrality in interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    се
    0.48
    li
    0.46
    h
    0.45
    ein
    0.44
    dir
    0.43
    ্না
    0.43
     ವಿಷಯ
    0.43
    d
    0.43
    čaj
    0.42
     মোটা
    0.42
    POSITIVE LOGITS
    outine
    0.45
     locking
    0.45
     Locking
    0.41
     Bucs
    0.40
    很是
    0.40
    尽
    0.40
    抻
    0.40
     evocative
    0.39
     Herpes
    0.39
     fortitude
    0.39
    Act Density 0.004%

    No Known Activations