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

    Neuronpedia

    INDEX
    Explanations

    immense pain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rmse
    0.42
     Longitudinal
    0.40
     yarns
    0.39
     Carolina
    0.39
    rms
    0.39
    otemporal
    0.38
     যৌ
    0.38
     Jose
    0.38
    consuming
    0.38
     Southeastern
    0.38
    POSITIVE LOGITS
    Berger
    0.58
     Berger
    0.52
    Thom
    0.51
     Thom
    0.50
     Fuer
    0.43
     ски
    0.42
     Folge
    0.41
     Bev
    0.40
     Zam
    0.40
    RetResult
    0.40
    Act Density 0.002%

    No Known Activations