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

    Neuronpedia

    INDEX
    Explanations

    on average

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fu
    0.21
     Introduce
    0.21
     Setup
    0.20
     разными
    0.19
    Introduce
    0.18
    Neg
    0.18
    ませんが
    0.18
    introduced
    0.18
     со
    0.18
    Introducing
    0.18
    POSITIVE LOGITS
     behalf
    0.29
     occasion
    0.27
     average
    0.25
     tenter
    0.24
     McMaster
    0.24
    slaught
    0.23
     top
    0.23
     par
    0.22
     horseback
    0.22
     occasione
    0.22
    Act Density 0.024%

    No Known Activations