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

    Neuronpedia

    INDEX
    Explanations

    likelihood and probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.58
    *,
    1.45
    ',
    1.44
    ,'
    1.38
    #,
    1.37
    ，
    1.32
    +,
    1.31
    ،
    1.30
    ’,
    1.30
    $,
    1.29
    POSITIVE LOGITS
     البته
    1.33
     notamment
    1.14
     spesso
    1.12
     oftentimes
    1.09
     thereby
    1.05
    同时也
    1.05
     magari
    1.04
     parfois
    1.03
     अक्सर
    1.02
     souvent
    0.99
    Act Density 0.224%

    No Known Activations