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

    Neuronpedia

    INDEX
    Explanations

    transactional verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fundamental
    0.46
    Fundamental
    0.45
    正在
    0.44
    Character
    0.43
     Character
    0.40
     Fundamental
    0.38
    character
    0.37
    Abstract
    0.37
     กําลัง
    0.37
     character
    0.37
    POSITIVE LOGITS
     bodo
    0.45
     judiciales
    0.41
     THEN
    0.41
    powerm
    0.41
    then
    0.40
    smtb
    0.40
    ultz
    0.39
     But
    0.39
     persone
    0.39
    umumkan
    0.38
    Act Density 0.000%

    No Known Activations