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

    Neuronpedia

    INDEX
    Explanations

    let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']>
    0.65
    )>
    0.63
    )">
    0.61
    ()">
    0.59
     ユ
    0.57
    ‴
    0.57
    单元
    0.56
    }^{*}=\
    0.56
     weißen
    0.56
     सुर्ख
    0.55
    POSITIVE LOGITS
    参加
    0.71
     Participant
    0.65
     Participants
    0.61
     emergency
    0.60
     participant
    0.60
     Reasonable
    0.59
     EAR
    0.59
    參加
    0.59
     earnings
    0.59
     eszköz
    0.58
    Act Density 0.123%

    No Known Activations