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

    Neuronpedia

    INDEX
    Explanations

    technical and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ερ
    0.46
     Brigade
    0.37
    ilder
    0.37
    yscanner
    0.37
     Zhe
    0.36
     bridging
    0.35
    brid
    0.34
    ektir
    0.33
     kock
    0.33
     bridged
    0.33
    POSITIVE LOGITS
    リモ
    0.36
     malfunctioning
    0.36
    واف
    0.36
     ಫಲ
    0.34
    辙
    0.34
    velocityX
    0.34
    csp
    0.33
    Mve
    0.33
    north
    0.33
    omitem
    0.33
    Act Density 0.000%

    No Known Activations