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

    Neuronpedia

    INDEX
    Explanations

    root of 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instantly
    0.54
     vrchol
    0.48
     instantaneously
    0.48
     itemprop
    0.46
     współ
    0.46
     appoint
    0.45
    ">→</
    0.45
     gwiaz
    0.44
     immediately
    0.44
     allege
    0.44
    POSITIVE LOGITS
    मध
    0.51
    gean
    0.49
    外出
    0.48
    igel
    0.48
    in
    0.47
    怠
    0.47
    aidh
    0.46
    bounds
    0.45
    高
    0.45
    ஞான
    0.45
    Act Density 0.001%

    No Known Activations