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

    Neuronpedia

    INDEX
    Explanations

    list items or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nº
    0.48
    (<
    0.42
    (+
    0.41
    directions
    0.39
    Administration
    0.38
     (/
    0.37
    ApiCalls
    0.37
     розта
    0.37
    磪
    0.37
    secretary
    0.36
    POSITIVE LOGITS
     b
    0.54
    a
    0.44
    ａ
    0.42
     sub
    0.40
     subdivided
    0.39
    b
    0.39
     profit
    0.37
     deren
    0.37
     этом
    0.37
    а
    0.37
    Act Density 0.004%

    No Known Activations