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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STRING
    -0.06
     bishops
    -0.06
    EX
    -0.06
     raw
    -0.06
    signals
    -0.06
    โก
    -0.06
    ER
    -0.06
     Carl
    -0.06
     독
    -0.06
    .thumbnail
    -0.06
    POSITIVE LOGITS
     Giang
    0.07
    /company
    0.07
    true
    0.07
     Forgotten
    0.06
     prefixed
    0.06
    ________
    0.06
     jailed
    0.06
    向
    0.06
     حم
    0.06
     говорит
    0.06
    Act Density 0.294%

    No Known Activations