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

    Neuronpedia

    INDEX
    Explanations

    pandas dataframe creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    veis
    0.39
     safer
    0.39
     frequented
    0.36
     subsided
    0.36
     stopped
    0.35
    sig
    0.35
     anxiously
    0.35
    }}=$
    0.34
    amid
    0.34
    cong
    0.34
    POSITIVE LOGITS
    𝙿
    0.39
     '*')
    0.38
    ！)
    0.38
    numpy
    0.36
    髮
    0.35
    延迟
    0.35
    𝙷
    0.35
     Monaten
    0.33
    ជាមួយនឹង
    0.33
    $)
    0.33
    Act Density 0.005%

    No Known Activations