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

    Neuronpedia

    INDEX
    Explanations

    we or they followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     titan
    0.46
     onboarding
    0.46
    <0x81>
    0.45
     Однако
    0.45
     behem
    0.45
    集团
    0.44
     will
    0.44
    albeit
    0.43
     ખૂબ
    0.43
    Однако
    0.42
    POSITIVE LOGITS
     www
    0.42
     ਜਾਂ
    0.42
     ją
    0.40
     കൂട
    0.40
     ((
    0.39
     pochod
    0.39
     altres
    0.39
     reside
    0.39
     enmity
    0.39
     wynosi
    0.39
    Act Density 0.034%

    No Known Activations