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

    Neuronpedia

    INDEX
    Explanations

    illegal, early, familiar contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.47
    Band
    0.45
    ותר
    0.44
     Bavaria
    0.42
     imponer
    0.42
    цен
    0.42
    asting
    0.41
     alli
    0.40
    Morris
    0.40
     cheer
    0.40
    POSITIVE LOGITS
     причинам
    0.51
     nút
    0.50
    蟎
    0.49
     ຂ
    0.48
    按钮
    0.48
     справед
    0.47
    isak
    0.47
     虽然
    0.47
    stepToken
    0.47
    এল
    0.46
    Act Density 0.001%

    No Known Activations