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

    Neuronpedia

    INDEX
    Explanations

    link resolvers and aggregators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bur
    0.43
     Кры
    0.39
     Bur
    0.39
     Johnny
    0.38
     Iván
    0.38
     JOH
    0.38
     légion
    0.38
    樯
    0.38
    ak
    0.37
    bfc
    0.37
    POSITIVE LOGITS
    oping
    0.49
    যুক্ত
    0.46
     to
    0.45
    omaly
    0.45
    edom
    0.44
    STATES
    0.44
    ロッパ
    0.44
    PERTIES
    0.42
     inactivation
    0.42
    嗇
    0.42
    Act Density 0.012%

    No Known Activations