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

    Neuronpedia

    INDEX
    Explanations

    last or latest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vert
    0.44
     authent
    0.40
     comm
    0.39
     Vert
    0.38
     knot
    0.38
     sharp
    0.37
     chunk
    0.37
     minim
    0.37
     vec
    0.37
     pointer
    0.36
    POSITIVE LOGITS
    Послед
    0.47
    lasti
    0.41
    sluš
    0.41
     Last
    0.40
     Muitos
    0.39
    𝒐
    0.39
    0.38
     الأخيرة
    0.38
    significant
    0.37
     Послед
    0.37
    Act Density 0.010%

    No Known Activations