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

    Neuronpedia

    INDEX
    Explanations

    placeholder for template inputsplaceholders from user inputcompany, customer, site, professor, date, your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     destabil
    0.42
     wagg
    0.40
     kinet
    0.40
     decomposition
    0.38
     anhyd
    0.38
     jednotliv
    0.38
     terroir
    0.38
     insufficiently
    0.38
     parto
    0.37
    oribus
    0.37
    POSITIVE LOGITS
     そして
    0.47
    www
    0.46
     বাড়ি
    0.44
    dbo
    0.43
    Ж
    0.42
    website
    0.41
    そして
    0.41
    displayName
    0.41
    пла
    0.40
    Ма
    0.40
    Act Density 0.035%

    No Known Activations