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

    Neuronpedia

    INDEX
    Explanations

    add or hide actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olar
    1.10
    ну
    1.06
    imento
    1.02
    deletion
    0.98
    wider
    0.97
    wars
    0.95
    വൃത്തി
    0.94
    ça
    0.90
    이는
    0.90
     maximum
    0.89
    POSITIVE LOGITS
    狽
    1.48
     titik
    1.33
    ాన్
    1.31
     tolle
    1.26
     gaji
    1.25
     ૩
    1.21
     Daryl
    1.21
     brasileira
    1.20
     tiga
    1.19
     Fernseh
    1.19
    Act Density 0.001%

    No Known Activations