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

    Neuronpedia

    INDEX
    Explanations

    code or technical documentation

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    	dx
    -0.08
     Zu
    -0.07
    Aaron
    -0.07
     delicious
    -0.07
     wicked
    -0.06
    뜨
    -0.06
    élé
    -0.06
    ien
    -0.06
    echa
    -0.06
     Вы
    -0.06
    POSITIVE LOGITS
    /tasks
    0.07
     THEN
    0.06
    _AM
    0.06
     mData
    0.06
    һ
    0.06
    .predicate
    0.06
    .head
    0.06
    -loader
    0.06
    'Re
    0.06
    _VIEW
    0.06
    Act Density 0.000%

    No Known Activations