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

    Neuronpedia

    INDEX
    Explanations

    descriptive qualities and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offsetting
    0.48
     زی
    0.47
     குற
    0.46
     கழி
    0.46
    分の
    0.45
     மோச
    0.45
     prévoit
    0.44
    償
    0.44
     instructing
    0.44
    avat
    0.44
    POSITIVE LOGITS
    ))
    0.57
    )，
    0.49
    Storm
    0.49
    )
    0.49
    )、
    0.47
    Trace
    0.45
     Storm
    0.44
    :\
    0.44
     الده
    0.44
    )،
    0.43
    Act Density 0.001%

    No Known Activations