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

    Neuronpedia

    INDEX
    Explanations

    making physical adjustments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.55
    0.55
     et
    0.53
     mutate
    0.50
     Mohawk
    0.50
     utk
    0.50
     Grove
    0.49
    anthem
    0.49
    }
    0.48
    acher
    0.48
    POSITIVE LOGITS
     ajustes
    1.05
     ajuste
    1.04
     adjustments
    0.98
    調整
    0.96
     Ajust
    0.92
     ajust
    0.87
     adjusts
    0.86
     Adjust
    0.85
    调整
    0.84
    Adjust
    0.84
    Act Density 0.036%

    No Known Activations