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

    Neuronpedia

    INDEX
    Explanations

    HTML attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ).
    0.64
     cmdlet
    0.63
     meson
    0.63
     निराश
    0.62
     '/',
    0.61
    omain
    0.61
     dik
    0.60
     '?
    0.60
     }.
    0.60
     `:
    0.59
    POSITIVE LOGITS
    ="
    2.26
    ='
    1.73
    =”
    1.72
    =\"
    1.61
     ="
    1.48
    ="-
    1.45
    ={
    1.44
    =\
    1.41
    =""
    1.40
    ="#
    1.39
    Act Density 0.085%

    No Known Activations