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

    Neuronpedia

    INDEX
    Explanations

    research paper citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    malloc
    -0.08
    _geo
    -0.07
     Yan
    -0.06
    isd
    -0.06
    .Sync
    -0.06
    PhoneNumber
    -0.06
    �
    -0.06
     Π
    -0.06
     critical
    -0.06
    ابق
    -0.06
    POSITIVE LOGITS
    ับท
    0.06
     Một
    0.06
    reon
    0.06
    φη
    0.06
    >]
    0.06
    _UID
    0.06
     你
    0.06
    ALE
    0.06
     prostoru
    0.06
    .original
    0.06
    Act Density 0.022%

    No Known Activations