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

    Neuronpedia

    INDEX
    Explanations

    html entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.36
    ployment
    0.35
     =-\
    0.33
    Sire
    0.33
    Palmer
    0.33
    avelength
    0.33
    OTTOM
    0.33
    ("")]
    0.33
    ﭜ
    0.33
     buddhav
    0.32
    POSITIVE LOGITS
    nbsp
    0.77
    ;&
    0.75
    amp
    0.74
     nbsp
    0.68
    &#
    0.67
    quot
    0.66
    &
    0.66
     amp
    0.66
    ">&
    0.63
     quot
    0.63
    Act Density 0.007%

    No Known Activations