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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     analysis
    0.37
     iteratively
    0.36
     graphical
    0.35
     sequences
    0.35
     structuring
    0.35
     timeframe
    0.34
     clinical
    0.33
    として
    0.33
     interwoven
    0.32
     effectively
    0.32
    POSITIVE LOGITS
    borhood
    0.40
     यकीन
    0.37
     puns
    0.37
     sabato
    0.37
    underwear
    0.36
     Tuesdays
    0.36
     alimony
    0.36
     cerveza
    0.36
     burrito
    0.35
     delicioso
    0.35
    Act Density 0.494%

    No Known Activations