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

    Neuronpedia

    INDEX
    Explanations

    tearing apart or ripping away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diffusion
    0.39
     Diffusion
    0.36
    关心
    0.36
    Shakespeare
    0.35
     Pareto
    0.35
     bytecode
    0.35
     Faker
    0.35
     ')[
    0.34
    漕
    0.34
    BinaryOperation
    0.34
    POSITIVE LOGITS
     pulled
    0.96
     pulling
    0.93
     Pull
    0.91
     pull
    0.91
    pull
    0.91
     pulls
    0.87
    Pull
    0.84
     ripping
    0.78
     plucked
    0.77
     apart
    0.75
    Act Density 0.019%

    No Known Activations