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

    Neuronpedia

    INDEX
    Explanations

    structured explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    歟
    0.37
     genomes
    0.37
     বলেও
    0.36
    ാനും
    0.35
    RationalValue
    0.35
     dimers
    0.34
     melodies
    0.34
    యి
    0.34
     další
    0.34
    "+"|".
    0.34
    POSITIVE LOGITS
     Basically
    0.51
     बेसिकली
    0.51
    It
    0.50
    दरअसल
    0.48
    :
    0.47
    What
    0.46
     दरअसल
    0.46
     Firstly
    0.46
     Specifically
    0.46
     it
    0.45
    Act Density 0.761%

    No Known Activations