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

    Neuronpedia

    INDEX
    Explanations

    YouTube advertising, code methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ữ
    0.38
    酝
    0.37
    પ્ત
    0.36
    പ്പെട്ടു
    0.35
     sogenannten
    0.35
     sogenannte
    0.34
     distract
    0.34
    )+"
    0.34
    ვლ
    0.34
    Logical
    0.34
    POSITIVE LOGITS
     \\
    0.39
    </h3>
    0.38
    essi
    0.38
     onerror
    0.38
     Frente
    0.37
     ngờ
    0.37
     Enf
    0.36
    岱
    0.35
    ֒
    0.34
     le
    0.34
    Act Density 0.000%

    No Known Activations