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

    Neuronpedia

    INDEX
    Explanations

    configuration keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    抟
    0.45
     Функ
    0.43
    মুখি
    0.42
     Simone
    0.41
     Guilford
    0.41
     funnel
    0.40
     ruk
    0.40
     सक्छ
    0.40
     selector
    0.39
     Wyn
    0.39
    POSITIVE LOGITS
    subnet
    0.38
     неде
    0.36
    ARIES
    0.35
    Net
    0.34
    amba
    0.34
    atten
    0.33
     meaningfully
    0.33
     compromising
    0.33
     longiore
    0.33
    inda
    0.32
    Act Density 0.001%

    No Known Activations