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

    Neuronpedia

    INDEX
    Explanations

    open standards and protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蝓
    0.41
     refracting
    0.41
     Cavendish
    0.40
    helby
    0.40
     lentils
    0.40
     potência
    0.40
     youtube
    0.39
     persian
    0.39
    礪
    0.39
     drenched
    0.38
    POSITIVE LOGITS
     standardized
    1.63
     standards
    1.58
     standardization
    1.54
     standardised
    1.52
    standards
    1.50
     standard
    1.45
     станда
    1.44
    standard
    1.41
     standardize
    1.41
     стандарта
    1.38
    Act Density 0.047%

    No Known Activations