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

    Neuronpedia

    INDEX
    Explanations

    variety of terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ma
    0.47
    elope
    0.45
    Slip
    0.44
    ional
    0.43
    lir
    0.43
    endtime
    0.42
    venture
    0.42
    Benchmarks
    0.42
    ﺅ
    0.42
    me
    0.41
    POSITIVE LOGITS
     Deutsches
    0.50
     Przed
    0.50
    푎
    0.49
     스
    0.47
     Ε
    0.47
     ג
    0.47
     câu
    0.46
     독일
    0.46
     QoS
    0.46
     землі
    0.45
    Act Density 0.001%

    No Known Activations