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

    Neuronpedia

    INDEX
    Explanations

    curly braces `{}`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.57
    ?)
    0.56
    u
    0.49
    ）
    0.48
    银
    0.46
    Overview
    0.46
    e
    0.45
    ）。
    0.45
    H
    0.45
    rund
    0.45
    POSITIVE LOGITS
    ຢູ່ໃນ
    0.50
     spese
    0.49
     originate
    0.48
     inviscid
    0.47
     renounce
    0.46
    ূলক
    0.46
     époque
    0.45
    ຂອງທ່ານ
    0.45
     ignoreString
    0.45
     solidify
    0.44
    Act Density 0.001%

    No Known Activations