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

    Neuronpedia

    INDEX
    Explanations

    modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Über
    0.50
    Common
    0.48
     Common
    0.46
     Privilege
    0.46
     Universal
    0.45
     Set
    0.44
    a
    0.44
     Friends
    0.44
     Service
    0.44
    John
    0.44
    POSITIVE LOGITS
     oxalic
    0.53
    운데
    0.47
     oncologist
    0.44
     senescence
    0.44
    方に
    0.43
     bicarbonate
    0.43
     incubated
    0.43
     alkaline
    0.43
    ূর্ন
    0.42
     ladle
    0.42
    Act Density 0.001%

    No Known Activations