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

    Neuronpedia

    INDEX
    Explanations

    Country, month, scenario, Bush, modern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lja
    0.49
     Telling
    0.49
    Hell
    0.46
     films
    0.46
    ין
    0.46
    Α
    0.45
     flora
    0.45
    তেও
    0.44
    咫
    0.44
     decompose
    0.44
    POSITIVE LOGITS
     \}$
    0.51
     اُن
    0.47
    áng
    0.47
     *);
    0.46
    returnValue
    0.46
     prevención
    0.45
    empê
    0.45
    车载
    0.44
    )_{
    0.43
     ஊழிய
    0.43
    Act Density 0.001%

    No Known Activations