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

    Neuronpedia

    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monday
    0.49
    iser
    0.48
     on
    0.47
    chel
    0.45
    ales
    0.45
     Mondays
    0.44
     Friday
    0.43
    ong
    0.43
    7
    0.43
    ley
    0.42
    POSITIVE LOGITS
    )،
    0.53
    )
    0.52
    ര്‍ന്ന്
    0.51
    艨
    0.51
     finalText
    0.50
    )、
    0.50
    斡
    0.49
    ),\
    0.49
    ᱱ
    0.49
     sequestration
    0.49
    Act Density 0.000%

    No Known Activations